Search

Deep learning networks have recently demonstrated yielded impressive progress for multi-exposure image fusion. However, how to restore realistic texture details while correcting color distortion is still a challenging problem to be solved. To alleviate the aforementioned issues, in this paper, we propose an attention-guided global-local adversarial learning network for fusing extreme exposure images in a coarse-to-fine manner. Firstly, the coarse fusion result is generated under the guidance of attention weight maps, which acquires the essential region of interest from both sides. Secondly, we formulate an edge loss function, along with a spatial feature transform layer, for refining the fusion process. So that it can take full use of the edge information to deal with blurry edges. Moreover, by incorporating global-local learning, our method can balance pixel intensity distribution and correct the color distortion on spatially varying source images from both image/patch perspectives. Such a global-local discriminator ensures all the local patches of the fused images align with realistic normal-exposure ones. Extensive experimental results on two publicly available datasets show that our method drastically outperforms state-of-the-art methods in visual inspection and objective analysis. Furthermore, sufficient ablation experiments prove that our method has significant advantages in generating high-quality fused results with appealing details, clear targets, and faithful color. Source code will be available at https://github.com/JinyuanLiu-CV/AGAL. [ABSTRACT FROM AUTHOR]

It is challenging to restore low-resolution (LR) images to super-resolution (SR) images with correct and clear details. Existing deep learning works almost neglect the inherent structural information of images, which acts as an important role for visual perception of SR results. In this paper, we design a hierarchical feature exploitation network to probe and preserve structural information in a multi-scale feature fusion manner. First, we propose a cross convolution upon traditional edge detectors to localize and represent edge features. Then, cross convolution blocks (CCBs) are designed with feature normalization and channel attention to consider the inherent correlations of features. Finally, we leverage multi-scale feature fusion group (MFFG) to embed the cross convolution blocks and develop the relations of structural features in different scales hierarchically, invoking a lightweight structure-preserving network named as Cross-SRN. Experimental results demonstrate the Cross-SRN achieves competitive or superior restoration performances against the state-of-the-art methods with accurate and clear structural details. Moreover, we set a criterion to select images with rich structural textures. The proposed Cross-SRN outperforms the state-of-the-art methods on the selected benchmark, which demonstrates that our network has a significant advantage in preserving edges. [ABSTRACT FROM AUTHOR]

Partial Label Learning (PLL) is a weakly supervised learning framework where each training instance is associated with more than one candidate label. This learning method is dedicated to finding out the true label for each training instance. Most of the current PLL algorithms directly disambiguate the candidate labels without correcting the disambiguated results, making the algorithms vulnerable to the influence of instances easily misjudged. In this paper, GraphDCN, an innovative disambiguation correction net with inductive graph representation learning model is proposed. GraphDCN consists of a disambiguation model and a correction model. For a given instance, the disambiguation model tries to fit its underlying ground-truth label through the candidate label distribution of the instances connected with the given one, while the correction model tries to maximize the distance between the disambiguated labels and non-candidate labels, and uses the label probability thresholds to correct the disambiguated labels that may be wrong. As the training goes on, both the disambiguation and correction models alternately and iteratively boost their performance. Moreover, when considering the implementation of the disambiguation model, a partial cross entropy formulation is proposed to estimate the ground-truth label loss by updating the ambiguity confidence matrix, which can be proved satisfying convergence in PLL. Simulation results reveal the overwhelming performance of GraphDCN. [ABSTRACT FROM AUTHOR]

As a challenging attempt to replace a traditional data structure with a learned model, this paper proposes a learned functional Bloom filter (L-FBF) for a key–value storage. The learned model in the proposed L-FBF learns the characteristics and the distribution of given data and classifies each input. It is shown through theoretical analysis that the L-FBF provides a lower search failure rate than a single FBF in the same memory size, while providing the same semantic guarantees. For model training, character-level neural networks are used with pretrained embeddings. In experiments, four types of different character-level neural networks are trained: a single gated recurrent unit (GRU), two GRUs, a single long short-term memory (LSTM), and a single one-dimensional convolutional neural network (1D-CNN). Experimental results prove the validity of theoretical results, and show that the L-FBF reduces the search failures by 82.8% to 83.9% when compared with a single FBF under the same amount of memory used. [ABSTRACT FROM AUTHOR]

Achieving microsecond-scale tail latency poses an extreme challenge to the conventional architecture of “NIC-OS-Application” in the face of high concurrent requests. Existing kernel-bypass network systems improve this situation significantly. Still, they cannot achieve load-aware in-server requests distribution, which in turn not only harms resource efficiency but, more importantly, beats the goal of squeezing tail latency. This paper proposes iBalancer, an in-server proactive load balancer for the kernel-bypass system, which aggressively handles NIC-side flow scheduling according to the load of threads on the processor-side. Furthermore, we propose a novel metric, “polling time interval (PTI),” to quantify the load of worker threads, which not only indicates utilization of the core bound to the worker thread but also reflects the differences in the processing time of different flows. By scheduling flows according to the metric PTI, iBalancer tends to average the queueing latencies of different flows, such as Set & Get operations for an in-memory key-value store. In addition, by decoupling flow scheduling from packet steering, iBalancer achieves a tail latency aware flow-to-core binding and preserves hardware-based request distribution among cores. The proposed system is evaluated and compared to mTCP and Shenango using two representative microsecond-scale network applications: Memcached KVS and a real-time deep-learning-based financial fraud identification application. Experimental results show that iBalancer can process up to 4.75 × and 1.55 × higher load over mTCP and Shenango under 500μs 99th percentile tail latency limit on Memcached. For the financial fraud identification application, iBalancer is able to process 4.56 × and 1.16 × higher load than mTCP and Shenango considering 900μs tail latency. [ABSTRACT FROM AUTHOR]

Accurate estimation and quantification of the corneal nerve fiber tortuosity in corneal confocal microscopy (CCM) is of great importance for disease understanding and clinical decision-making. However, the grading of corneal nerve tortuosity remains a great challenge due to the lack of agreements on the definition and quantification of tortuosity. In this paper, we propose a fully automated deep learning method that performs image-level tortuosity grading of corneal nerves, which is based on CCM images and segmented corneal nerves to further improve the grading accuracy with interpretability principles. The proposed method consists of two stages: 1) A pre-trained feature extraction backbone over ImageNet is fine-tuned with a proposed novel bilinear attention (BA) module for the prediction of the regions of interest (ROIs) and coarse grading of the image. The BA module enhances the ability of the network to model long-range dependencies and global contexts of nerve fibers by capturing second-order statistics of high-level features. 2) An auxiliary tortuosity grading network (AuxNet) is proposed to obtain an auxiliary grading over the identified ROIs, enabling the coarse and additional gradings to be finally fused together for more accurate final results. The experimental results show that our method surpasses existing methods in tortuosity grading, and achieves an overall accuracy of 85.64% in four-level classification. We also validate it over a clinical dataset, and the statistical analysis demonstrates a significant difference of tortuosity levels between healthy control and diabetes group. We have released a dataset with 1500 CCM images and their manual annotations of four tortuosity levels for public access. The code is available at: https://github.com/iMED-Lab/TortuosityGrading. [ABSTRACT FROM AUTHOR]

Fast and accurate MRI image reconstruction from undersampled data is crucial in clinical practice. Deep learning based reconstruction methods have shown promising advances in recent years. However, recovering fine details from undersampled data is still challenging. In this paper, we introduce a novel deep learning based method, Pyramid Convolutional RNN (PC-RNN), to reconstruct images from multiple scales. Based on the formulation of MRI reconstruction as an inverse problem, we design the PC-RNN model with three convolutional RNN (ConvRNN) modules to iteratively learn the features in multiple scales. Each ConvRNN module reconstructs images at different scales and the reconstructed images are combined by a final CNN module in a pyramid fashion. The multi-scale ConvRNN modules learn a coarse-to-fine image reconstruction. Unlike other common reconstruction methods for parallel imaging, PC-RNN does not employ coil sensitive maps for multi-coil data and directly model the multiple coils as multi-channel inputs. The coil compression technique is applied to standardize data with various coil numbers, leading to more efficient training. We evaluate our model on the fastMRI knee and brain datasets and the results show that the proposed model outperforms other methods and can recover more details. The proposed method is one of the winner solutions in the 2019 fastMRI competition. [ABSTRACT FROM AUTHOR]

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the ‘image-to-image’ translation genre which requires some additional computational modules not present in classification. This paper seeks to bridge this gap by designing generic efficient modules which can replace essential components used in contemporary deep learning based image restoration networks. We also present and analyse our results highlighting the drawbacks of applying depthwise separable convolutional kernel (a popular method for efficient classification network) for sub-pixel convolution based upsampling (a popular upsampling strategy for low-level vision applications). This shows that concepts from domain of classification cannot always be seamlessly integrated into ‘image-to-image’ translation tasks. We extensively validate our findings on three popular tasks of image inpainting, denoising and super-resolution. Our results show that proposed networks consistently output visually similar reconstructions compared to full capacity baselines with significant reduction of parameters, memory footprint and execution speeds on contemporary mobile devices. [ABSTRACT FROM AUTHOR]

This paper proposes a novel data driven framework for detecting topology transitions in a distribution network. The framework analyzes data from phasor measurement units (PMUs) and relies on the fact that changes in network topology results in changes in the structure and admittance of the network. Using voltage and current phasors recorded by PMUs, the proposed method approximates network parameters using an ensemble-based deep learning model and thus, it does not require any knowledge of network parameters and load models. Using the prediction error of the proposed model, a connectivity matrix which shows the status of switches is constructed. In contrast to other methods, this proposed framework does not require a library of voltage and current transients associated with possible network transitions. It can also detect simultaneous switching actions and is robust to noise and load variations. The model yields a lower error detection rate, and its performance is validated using a modified version of the IEEE 33 bus network and a real feeder located in Queensland, Australia, under full and partial observability conditions. The proposed model has also been compared with another data driven method in terms of inference time and error detection rates. [ABSTRACT FROM AUTHOR]

In order to reduce the dependence on accumulated experience that is difficult to replicate for the human dispatchers to make power generation scheduling more automatically, quickly, and intelligently, higher requirements are placed on the level of the auxiliary decision-making system. In this paper, a short-term scheduling problem was treated as a regression task that concentrates on how to learn a reliable statistic model that concludes the intrinsic logic of the dispatching policy from extensive historical dispatching experience. In this way, since Kullback-Leibler distance can better measure the distance between two distributions, we designed a novel GAN-based learning method for the scheduling task. Also, we proposed a feasible framework that combines the stage of learning, decision-making, and deployment to support the practical implementation of the proposed algorithm. In the experiment, a real case that takes short-term scheduling tasks on a regional large-scale power system is considered in our experiments. As a result, the comparison of several methods further shows the superiority of the proposed GAN-based method under our implementations. [ABSTRACT FROM AUTHOR]

To solve the low spatial and/or temporal resolution problem which the conventional hyperspectral cameras often suffer from, coded hyperspectral imaging systems have attracted more attention recently. Recovering a hyperspectral image (HSI) from its corresponding coded image is an ill-posed inverse problem, and learning accurate prior of HSI is essential to solve this inverse problem. In this paper, we present an effective convolutional neural network (CNN) based method for coded HSI reconstruction, which learns the deep prior from the external dataset as well as the internal information of input coded image with spatial-spectral constraint. Specifically, we first develop a CNN-based channel attention reconstruction network to effectively exploit the spatial-spectral correlation of the HSI. Then, the reconstruction network is learned by leveraging an arbitrary external hyperspectral dataset to exploit the general spatial-spectral correlation under adversarial loss. Finally, we customize the network by internal learning with spatial-spectral constraint and total variation regularization for each coded image, which can make use of the internal imaging model to learn specific prior for current desirable image and effectively avoids overfitting. Experimental results using both synthetic data and real images show that our method outperforms the state-of-the-art methods on several popular coded hyperspectral imaging systems under both comprehensive quantitative metrics and perceptive quality. [ABSTRACT FROM AUTHOR]

Neural architecture search (NAS) has attracted a lot of attention and has been illustrated to bring tangible benefits in a large number of applications in the past few years. Architecture topology and architecture size have been regarded as two of the most important aspects for the performance of deep learning models and the community has spawned lots of searching algorithms for both of those aspects of the neural architectures. However, the performance gain from these searching algorithms is achieved under different search spaces and training setups. This makes the overall performance of the algorithms incomparable and the improvement from a sub-module of the searching model unclear. In this paper, we propose NATS-Bench, a unified benchmark on searching for both topology and size, for (almost) any up-to-date NAS algorithm. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets. We analyze the validity of our benchmark in terms of various criteria and performance comparison of all candidates in the search space. We also show the versatility of NATS-Bench by benchmarking 13 recent state-of-the-art NAS algorithms on it. All logs and diagnostic information trained using the same setup for each candidate are provided. This facilitates a much larger community of researchers to focus on developing better NAS algorithms in a more comparable and computationally effective environment. All codes are publicly available at: https://xuanyidong.com/assets/projects/NATS-Bench. [ABSTRACT FROM AUTHOR]

Among the greatest of the challenges of minimally invasive surgery (MIS) is the inadequate visualisation of the surgical field through keyhole incisions. Moreover, occlusions caused by instruments or bleeding can completely obfuscate anatomical landmarks, reduce surgical vision and lead to iatrogenic injury. The aim of this paper is to propose an unsupervised end-to-end deep learning framework, based on fully convolutional neural networks to reconstruct the view of the surgical scene under occlusions and provide the surgeon with intraoperative see-through vision in these areas. A novel generative densely connected encoder-decoder architecture has been designed which enables the incorporation of temporal information by introducing a new type of 3D convolution, the so called 3D partial convolution, to enhance the learning capabilities of the network and fuse temporal and spatial information. To train the proposed framework, a unique loss function has been proposed which combines feature matching, reconstruction, style, temporal and adversarial loss terms, for generating high fidelity image reconstructions. Advancing the state-of-the-art, our method can reconstruct the underlying view obstructed by irregularly shaped occlusions of divergent size, location and orientation. The proposed method has been validated on in vivo MIS video data, as well as natural scenes on a range of occlusion-to-image (OIR) ratios. It has also been compared against the latest video inpainting models in terms of image reconstruction quality using different assessment metrics. The performance evaluation analysis verifies the superiority of our proposed method and its potential clinical value. [ABSTRACT FROM AUTHOR]

Gait is a unique biometric feature that can be recognized at a distance; thus, it has broad applications in crime prevention, forensic identification, and social security. To portray a gait, existing gait recognition methods utilize either a gait template which makes it difficult to preserve temporal information, or a gait sequence that maintains unnecessary sequential constraints and thus loses the flexibility of gait recognition. In this paper, we present a novel perspective that utilizes gait as a deep set, which means that a set of gait frames are integrated by a global-local fused deep network inspired by the way our left- and right-hemisphere processes information to learn information that can be used in identification. Based on this deep set perspective, our method is immune to frame permutations, and can naturally integrate frames from different videos that have been acquired under different scenarios, such as diverse viewing angles, different clothes, or different item-carrying conditions. Experiments show that under normal walking conditions, our single-model method achieves an average rank-1 accuracy of 96.1 percent on the CASIA-B gait dataset and an accuracy of 87.9 percent on the OU-MVLP gait dataset. Under various complex scenarios, our model also exhibits a high level of robustness. It achieves accuracies of 90.8 and 70.3 percent on CASIA-B under bag-carrying and coat-wearing walking conditions respectively, significantly outperforming the best existing methods. Moreover, the proposed method maintains a satisfactory accuracy even when only small numbers of frames are available in the test samples; for example, it achieves 85.0 percent on CASIA-B even when using only 7 frames. The source code has been released at https://github.com/AbnerHqC/GaitSet. [ABSTRACT FROM AUTHOR]

Human-object interaction (HOI) Detection is an important problem to understand how humans interact with objects. In this paper, we explore Interactiveness Knowledge which indicates whether human and object interact with each other or not. We found that interactiveness knowledge can be learned across HOI datasets and alleviate the gap between diverse HOI category settings. Our core idea is to exploit an Interactiveness Network to learn the general interactiveness knowledge from multiple HOI datasets and perform Non-Interaction Suppression before HOI classification in inference. On account of the generalization of interactiveness, interactiveness network is a transferable knowledge learner and can be cooperated with any HOI detection models to achieve desirable results. We utilize the human instance and body part features together to learn the interactiveness in hierarchical paradigm, i.e., instance-level and body part-level interactivenesses. Thereafter, a consistency task is proposed to guide the learning and extract deeper interactive visual clues. We extensively evaluate the proposed method on HICO-DET, V-COCO, and a newly constructed HAKE-HOI dataset. With the learned interactiveness, our method outperforms state-of-the-art HOI detection methods, verifying its efficacy and flexibility. Code is available at https://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a big leap in automatic visual saliency detection attributed to advances in deep learning, especially Convolutional Neural Networks (CNNs). However, inferring the saliency of each image part separately, as was adopted by most CNNs methods, inevitably leads to an incomplete segmentation of the salient object. In this paper, we describe how to use the property of part-object relations endowed by the Capsule Network (CapsNet) to solve the problems that fundamentally hinge on relational inference for visual saliency detection. Concretely, we put in place a two-stream strategy, termed Two-Stream Part-Object RelaTional Network (TSPORTNet), to implement CapsNet, aiming to reduce both the network complexity and the possible redundancy during capsule routing. Additionally, taking into account the correlations of capsule types from the preceding training images, a correlation-aware capsule routing algorithm is developed for more accurate capsule assignments at the training stage, which also speeds up the training dramatically. By exploring part-object relationships, TSPORTNet produces a capsule wholeness map, which in turn aids multi-level features in generating the final saliency map. Experimental results on five widely-used benchmarks show that our framework consistently achieves state-of-the-art performance. The code can be found on https://github.com/liuyi1989/TSPORTNet. [ABSTRACT FROM AUTHOR]

Intelligent reflecting surface (IRS) is a promising new technology that is able to create a favorable wireless signal propagation environment by collaboratively reconfiguring the passive reflecting elements yet with low hardware and energy cost. In IRS-aided wireless communication systems, channel modeling is a fundamental task for communication algorithm design and performance optimization, which however is also very challenging since in-depth domain knowledge and technical expertise in radio signal propagations are required, especially for modeling the high-dimensional cascaded base station (BS)-IRS and IRS-user channels (also referred to as the reflected channels). In this paper, we propose a model-driven generative adversarial network (GAN)-based channel modeling framework to autonomously learn the reflected channel distribution, without complex theoretical analysis or data processing. The designed GAN (also named as IRS-GAN) is trained to reach the Nash equilibrium of a minimax game between a generative model and a discriminative model. For the single-user case, we propose to incorporate the special structure of the reflected channels into the design of the generative model. While for the multiuser case, we extend the IRS-GAN and present a multiuser IRS-GAN (abbreviated as IRS-GAN-M), where the distributions of the reflected channels associated with different users are learned simultaneously with reduced number of network parameters (as compared to the naive scheme that assigns a dedicated IRS-GAN for each user). Moreover, theoretical analysis is presented to prove that the minimax game in the IRS-GAN-M framework has a global optimum if the generative and discriminative models are given with enough capacity. Simulation results are presented to validate the effectiveness of the proposed IRS-GAN framework. [ABSTRACT FROM AUTHOR]

Light field imaging, which captures both spatial and angular information, improves user immersion by enabling post-capture actions, such as refocusing and changing view perspective. However, light fields represent very large volumes of data with a lot of redundancy that coding methods try to remove. State-of-the-art coding methods indeed usually focus on improving compression efficiency and overlook other important features in light field compression such as scalability. In this paper, we propose a novel light field image compression method that enables (i) viewport scalability, (ii) quality scalability, (iii) spatial scalability, (iv) random access, and (v) uniform quality distribution among viewports, while keeping compression efficiency high. To this end, light fields in each spatial resolution are divided into sequential viewport layers, and viewports in each layer are encoded using the previously encoded viewports. In each viewport layer, the available viewports are used to synthesize intermediate viewports using a video interpolation deep learning network. The synthesized views are used as virtual reference images to enhance the quality of intermediate views. An image super-resolution method is applied to improve the quality of the lower spatial resolution layer. The super-resolved images are also used as virtual reference images to improve the quality of the higher spatial resolution layer. The proposed structure also improves the flexibility of light field streaming, provides random access to the viewports, and increases error resiliency. The experimental results demonstrate that the proposed method achieves a high compression efficiency and it can adapt to the display type, transmission channel, network condition, processing power, and user needs. [ABSTRACT FROM AUTHOR]

Semantic segmentation methods based on deep neural networks have achieved great success in recent years. However, training such deep neural networks relies heavily on a large number of images with accurate pixel-level labels, which requires a huge amount of human effort, especially for large-scale remote sensing images. In this paper, we propose a point-based weakly supervised learning framework called the deep bilateral filtering network (DBFNet) for the semantic segmentation of remote sensing images. Compared with pixel-level labels, point annotations are usually sparse and cannot reveal the complete structure of the objects; they also lack boundary information, thus resulting in incomplete prediction within the object and the loss of object boundaries. To address these problems, we incorporate the bilateral filtering technique into deeply learned representations in two respects. First, since a target object contains smooth regions that always belong to the same category, we perform deep bilateral filtering (DBF) to filter the deep features by a nonlinear combination of nearby feature values, which encourages the nearby and similar features to become closer, thus achieving a consistent prediction in the smooth region. In addition, the DBF can distinguish the boundary by enlarging the distance between the features on different sides of the edge, thus preserving the boundary information well. Experimental results on two widely used datasets, the ISPRS 2-D semantic labeling Potsdam and Vaihingen datasets, demonstrate that our proposed DBFNet can achieve a highly competitive performance compared with state-of-the-art fully-supervised methods. Code is available at https://github.com/Luffy03/DBFNet. [ABSTRACT FROM AUTHOR]

Hyperspectral videos can provide the spatial, spectral, and motion information of targets, which makes it possible to track camouflaged targets that are similar to the background. However, hyperspectral object tracking is a challenging task, due to the huge hyperspectral video data dimension and the “data hungry” problem for the model training. Insufficient training data can seriously interfere with the accuracy and generalization of the tracking models. In this paper, a dual deep Siamese network framework for hyperspectral object tracking (SiamHYPER) is proposed for learning a hyperspectral tracker from a pretrained RGB tracker in the case of the “data hungry” problem. Specifically, in addition to a pretrained RGB-based Siamese tracker, a hyperspectral target-aware module is designed to mine the spectral information during the target prediction, and a spatial-spectral cross-attention module is introduced to further fuse the deep spatial and spectral features extracted from the RGB tracker and the hyperspectral target-aware module. Benefiting from the guidance training of the RGB tracker, a robust hyperspectral object tracker can be trained effectively with only a small number of hyperspectral video samples, to overcome the “data hungry” problem. In the experiments conducted in this study, the SiamHYPER framework was verified using SiamBAN and SiamRPN++, with 13 000 frames of hyperspectral videos for training, and achieved the best performance on the publicly available hyperspectral dataset released as part of the WHISPERS Hyperspectral Object Tracking Challenge. The area under the curve (AUC) of SiamHYPER was increased by nearly 8.9% and 7.2%, respectively, when compared with the current state-of-the-art RGB-based and hyperspectral trackers. In addition, the processing speed of SiamHYPER was 19 FPS, which is much higher than that of the current state-of-the-art hyperspectral trackers. The source code is available at zhenliuzhenqi/HOT: Hyperspectral object tracking (github.com). [ABSTRACT FROM AUTHOR]

Acoustic images are an emergent data modality for multimodal scene understanding. Such images have the peculiarity of distinguishing the spectral signature of the sound coming from different directions in space, thus providing a richer information as compared to that derived from single or binaural microphones. However, acoustic images are typically generated by cumbersome and costly microphone arrays which are not as widespread as ordinary microphones. This paper shows that it is still possible to generate acoustic images from off-the-shelf cameras equipped with only a single microphone and how they can be exploited for audio-visual scene understanding. We propose three architectures inspired by Variational Autoencoder, U-Net and adversarial models, and we assess their advantages and drawbacks. Such models are trained to generate spatialized audio by conditioning them to the associated video sequence and its corresponding monaural audio track. Our models are trained using the data collected by a microphone array as ground truth. Thus they learn to mimic the output of an array of microphones in the very same conditions. We assess the quality of the generated acoustic images considering standard generation metrics and different downstream tasks (classification, cross-modal retrieval and sound localization). We also evaluate our proposed models by considering multimodal datasets containing acoustic images, as well as datasets containing just monaural audio signals and RGB video frames. In all of the addressed downstream tasks we obtain notable performances using the generated acoustic data, when compared to the state of the art and to the results obtained using real acoustic images as input. [ABSTRACT FROM AUTHOR]

Modern top-performing object detectors depend heavily on backbone networks, whose advances bring consistent performance gains through exploring more effective network structures. In this paper, we propose a novel and flexible backbone framework, namely CBNet, to construct high-performance detectors using existing open-source pre-trained backbones under the pre-training fine-tuning paradigm. In particular, CBNet architecture groups multiple identical backbones, which are connected through composite connections. Specifically, it integrates the high- and low-level features of multiple identical backbone networks and gradually expands the receptive field to more effectively perform object detection. We also propose a better training strategy with auxiliary supervision for CBNet-based detectors. CBNet has strong generalization capabilities for different backbones and head designs of the detector architecture. Without additional pre-training of the composite backbone, CBNet can be adapted to various backbones (i.e., CNN-based vs. Transformer-based) and head designs of most mainstream detectors (i.e., one-stage vs. two-stage, anchor-based vs. anchor-free-based). Experiments provide strong evidence that, compared with simply increasing the depth and width of the network, CBNet introduces a more efficient, effective, and resource-friendly way to build high-performance backbone networks. Particularly, our CB-Swin-L achieves 59.4% box AP and 51.6% mask AP on COCO test-dev under the single-model and single-scale testing protocol, which are significantly better than the state-of-the-art results (i.e., 57.7% box AP and 50.2% mask AP) achieved by Swin-L, while reducing the training time by $6\times $. With multi-scale testing, we push the current best single model result to a new record of 60.1% box AP and 52.3% mask AP without using extra training data. Code is available at https://github.com/VDIGPKU/CBNetV2 . [ABSTRACT FROM AUTHOR]

Recently, deep learning based multispectral (MS) and panchromatic (PAN) image fusion methods have been proposed, which extracted features automatically and hierarchically by a series of non-linear transformations to model the complicated imaging discrepancy. But they always pay more attention to the extraction and compensation of spatial details and use the mean squared error or mean absolute error as a loss function, regardless of the preservation of spectral information contained in multispectral images. For the sake of the improvements in both spatial and spectral resolution, this paper presents a novel fusion model that takes the spectral preservation into consideration, and learns the spectral cues from the process of generating a spectrally refined multispectral image, which is constrained by a spectral loss between the generated image and the reference image. Then these spectral cues are used to modulate the PAN features to obtain final fusion result. Experimental results on reduced-resolution and full-resolution datasets demonstrate that the proposed method can obtain a better fusion result in terms of visual inspection and evaluation indices when compared with current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Visible-infrared person re-identification (VI-ReID) task aims to retrieve the same person between visible and infrared images. VI-ReID is challenging as the images captured by different spectra present large cross-modality discrepancy. Many methods adopt a two-stream network and design additional constraint conditions to extract shared features for different modalities. However, the interaction between the feature extraction processes of different modalities is rarely considered. In this paper, a partially interactive collaboration method is proposed to exploit the complementary information of different modalities to reduce the modality gap for VI-ReID. Specifically, the proposed method is achieved in a partially interactive-shared architecture: collaborative shallow layers and shared deep layers. The collaborative shallow layers consider the interaction between modality-specific features of different modalities, encouraging the feature extraction processes of different modalities constrain each other to enhance feature representations. The shared deep layers further embed the modality-specific features to a common space to endow them the same identity discriminability. To ensure the interactive collaborative learning implement effectively, the conventional loss and collaborative loss are utilized jointly to train the whole network. Extensive experiments on two publicly available VI-ReID datasets verify the superiority of the proposed PIC method. Specifically, the proposed method achieves a rank-1 accuracy of 83.6% and 57.5% on RegDB and SYSU-MM01 datasets, respectively. [ABSTRACT FROM AUTHOR]

Well-known compressed sensing (CS) is widely used in image acquisition and reconstruction. However, accurately reconstructing images from measurements at low sampling rates remains a considerable challenge. In this paper, we propose a novel Transformer-based hybrid architecture (dubbed TransCS) to achieve high-quality image CS. In the sampling module, TransCS adopts a trainable sensing matrix strategy that gains better image reconstruction by learning the structural information from the training images. In the reconstruction module, inspired by the powerful long-distance dependence modelling capacity of the Transformer, a customized iterative shrinkage-thresholding algorithm (ISTA)-based Transformer backbone that iteratively works with gradient descent and soft threshold operation is designed to model the global dependency among image subblocks. Moreover, the auxiliary convolutional neural network (CNN) is introduced to capture the local features of images. Therefore, the proposed hybrid architecture that integrates the customized ISTA-based Transformer backbone with CNN can gain high-performance reconstruction for image compressed sensing. The experimental results demonstrate that our proposed TransCS obtains superior reconstruction quality and noise robustness on several public benchmark datasets compared with other state-of-the-art methods. Our code is available on TransCS. [ABSTRACT FROM AUTHOR]

High-precision road detection from very high resolution (VHR) remote sensing images has broad application value. However, the most advanced deep learning based methods often fail to identify roads when there is a distribution discrepancy between the training samples and test samples, due to their limited generalization ability. In this paper, to address this problem, an open-source data-driven domain-specific representation (OSM-DOER) framework is proposed for cross-domain road detection. On the one hand, as the spatial structure information of the source and target domains is similar, but the texture information is different, the domain-specific representation (DOER) framework is proposed, which not only aligns the distributions of the spatial structure information, but also learns the domain-specific texture information. Furthermore, in order to enhance the representation of the target domain data distribution, open-source and freely available OpenStreetMap (OSM) road centerline data are utilized to generate target domain samples, which are then used in the network training as the supervised information for the target domain. Finally, to verify the superiority of the proposed OSM-DOER framework, we conducted extensive experiments with the public SpaceNet and DeepGlobe road datasets, and large-scale road datasets from Birmingham in the UK and Shanghai in China. The experimental results demonstrate that the proposed OSM-DOER framework shows obvious advantages over the mainstream road detection methods, and the use of OSM road centerline data has great potential for the road detection task. [ABSTRACT FROM AUTHOR]

Due to the wavelength-dependent light attenuation, refraction and scattering, underwater images usually suffer from color distortion and blurred details. However, due to the limited number of paired underwater images with undistorted images as reference, training deep enhancement models for diverse degradation types is quite difficult. To boost the performance of data-driven approaches, it is essential to establish more effective learning mechanisms that mine richer supervised information from limited training sample resources. In this paper, we propose a novel underwater image enhancement network, called SGUIE-Net, in which we introduce semantic information as high-level guidance via region-wise enhancement feature learning. Accordingly, we propose semantic region-wise enhancement module to better learn local enhancement features for semantic regions with multi-scale perception. After using them as complementary features and feeding them to the main branch, which extracts the global enhancement features on the original image scale, the fused features bring semantically consistent and visually superior enhancements. Extensive experiments on the publicly available datasets and our proposed dataset demonstrate the impressive performance of SGUIE-Net. The code and proposed dataset are available at https://trentqq.github.io/SGUIE-Net.html . [ABSTRACT FROM AUTHOR]

Generation of a 3D model of an object from multiple views has a wide range of applications. Different parts of an object would be accurately captured by a particular view or a subset of views in the case of multiple views. In this paper, a novel coarse-to-fine network (C2FNet) is proposed for 3D point cloud generation from multiple views. C2FNet generates subsets of 3D points that are best captured by individual views with the support of other views in a coarse-to-fine way, and then fuses these subsets of 3D points to a whole point cloud. It consists of a coarse generation module where coarse point clouds are constructed from multiple views by exploring the cross-view spatial relations, and a fine generation module where the coarse point cloud features are refined under the guidance of global consistency in appearance and context. Extensive experiments on the benchmark datasets have demonstrated that the proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

State-of-the-art 2D image compression schemes rely on the power of convolutional neural networks (CNNs). Although CNNs offer promising perspectives for 2D image compression, extending such models to omnidirectional images is not straightforward. First, omnidirectional images have specific spatial and statistical properties that can not be fully captured by current CNN models. Second, basic mathematical operations composing a CNN architecture, e.g., translation and sampling, are not well-defined on the sphere. In this paper, we study the learning of representation models for omnidirectional images and propose to use the properties of HEALPix uniform sampling of the sphere to redefine the mathematical tools used in deep learning models for omnidirectional images. In particular, we: i) propose the definition of a new convolution operation on the sphere that keeps the high expressiveness and the low complexity of a classical 2D convolution; ii) adapt standard CNN techniques such as stride, iterative aggregation, and pixel shuffling to the spherical domain; and then iii) apply our new framework to the task of omnidirectional image compression. Our experiments show that our proposed on-the-sphere solution leads to a better compression gain that can save 13.7% of the bit rate compared to similar learned models applied to equirectangular images. Also, compared to learning models based on graph convolutional networks, our solution supports more expressive filters that can preserve high frequencies and provide a better perceptual quality of the compressed images. Such results demonstrate the efficiency of the proposed framework, which opens new research venues for other omnidirectional vision tasks to be effectively implemented on the sphere manifold. [ABSTRACT FROM AUTHOR]

Most existing RGB-D salient object detection (SOD) methods are primarily focusing on cross-modal and cross-level saliency fusion, which has been proved to be efficient and effective. However, these methods still have a critical limitation, i.e., their fusion patterns – typically the combination of selective characteristics and its variations, are too highly dependent on the network’s non-linear adaptability. In such methods, the balances between RGB and D (Depth) are formulated individually considering the intermediate feature slices, but the relation at the modality level may not be learned properly. The optimal RGB-D combinations differ depending on the RGB-D scenarios, and the exact complementary status is frequently determined by multiple modality-level factors, such as D quality, the complexity of the RGB scene, and degree of harmony between them. Therefore, given the existing approaches, it may be difficult for them to achieve further performance breakthroughs, as their methodologies belong to some methods that are somewhat less modality sensitive. To conquer this problem, this paper presents the Modality-aware Decoder (MaD). The critical technical innovations include a series of feature embedding, modality reasoning, and feature back-projecting and collecting strategies, all of which upgrade the widely-used multi-scale and multi-level decoding process to be modality-aware. Our MaD achieves competitive performance over other state-of-the-art (SOTA) models without using any fancy tricks in the decoder’s design. Codes and results will be publicly available at https://github.com/MengkeSong/MaD. [ABSTRACT FROM AUTHOR]

Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images. Creating or finding satisfying lighting conditions, in reality, is laborious and time-consuming, so it is of great value to develop a technology to manipulate illumination in an image as post-processing. Although previous works have explored techniques based on the physical viewpoint for relighting images, extensive supervisions and prior knowledge are necessary to generate reasonable images, restricting the generalization ability of these works. In contrast, we take the viewpoint of image-to-image translation and implicitly merge ideas of the conventional physical viewpoint. In this paper, we present an Illumination-Aware Network (IAN) which follows the guidance from hierarchical sampling to progressively relight a scene from a single image with high efficiency. In addition, an Illumination-Aware Residual Block (IARB) is designed to approximate the physical rendering process and to extract precise descriptors of light sources for further manipulations. We also introduce a depth-guided geometry encoder for acquiring valuable geometry- and structure-related representations once the depth information is available. Experimental results show that our proposed method produces better quantitative and qualitative relighting results than previous state-of-the-art methods. The code and models are publicly available on https://github.com/NK-CS-ZZL/IAN. [ABSTRACT FROM AUTHOR]

Deep learning (DL) based hyperspectral images (HSIs) denoising approaches directly learn the nonlinear mapping between noisy and clean HSI pairs. They usually do not consider the physical characteristics of HSIs. This drawback makes the models lack interpretability that is key to understanding their denoising mechanism and limits their denoising ability. In this paper, we introduce a novel model-guided interpretable network for HSI denoising to tackle this problem. Fully considering the spatial redundancy, spectral low-rankness, and spectral-spatial correlations of HSIs, we first establish a subspace-based multidimensional sparse (SMDS) model under the umbrella of tensor notation. After that, the model is unfolded into an end-to-end network named SMDS-Net, whose fundamental modules are seamlessly connected with the denoising procedure and optimization of the SMDS model. This makes SMDS-Net convey clear physical meanings, i.e., learning the low-rankness and sparsity of HSIs. Finally, all key variables are obtained by discriminative training. Extensive experiments and comprehensive analysis on synthetic and real-world HSIs confirm the strong denoising ability, strong learning capability, promising generalization ability, and high interpretability of SMDS-Net against the state-of-the-art HSI denoising methods. The source code and data of this article will be made publicly available at https://github.com/bearshng/smds-net for reproducible research. [ABSTRACT FROM AUTHOR]

Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i.e., target domain. One common practice is to train the model on both labeled source-domain data and unlabeled target-domain data. Yet the learned models are usually biased due to the strong supervision of the source domain. Most researchers adopt the early-stopping strategy to prevent over-fitting, but when to stop training remains a challenging problem since the lack of the target-domain validation set. In this paper, we propose one efficient bootstrapping method, called Adaboost Student, explicitly learning complementary models during training and liberating users from empirical early stopping. Adaboost Student combines deep model learning with the conventional training strategy, i.e., adaptive boosting, and enables interactions between learned models and the data sampler. We adopt one adaptive data sampler to progressively facilitate learning on hard samples and aggregate “weak” models to prevent over-fitting. Extensive experiments show that (1) Without the need to worry about the stopping time, AdaBoost Student provides one robust solution by efficient complementary model learning during training. (2) AdaBoost Student is orthogonal to most domain adaptation methods, which can be combined with existing approaches to further improve the state-of-the-art performance. We have achieved competitive results on three widely-used scene segmentation domain adaptation benchmarks. [ABSTRACT FROM AUTHOR]

Recently, embedding and metric-based few-shot learning (FSL) has been introduced into hyperspectral image classification (HSIC) and achieved impressive progress. To further enhance the performance with few labeled samples, we in this paper propose a novel FSL framework for HSIC with a class-covariance metric (CMFSL). Overall, the CMFSL learns global class representations for each training episode by interactively using training samples from the base and novel classes, and a synthesis strategy is employed on the novel classes to avoid overfitting. During the meta-training and meta-testing, the class labels are determined directly using the Mahalanobis distance measurement rather than an extra classifier. Benefiting from the task-adapted class-covariance estimations, the CMFSL can construct more flexible decision boundaries than the commonly used Euclidean metric. Additionally, a lightweight cross-scale convolutional network (LXConvNet) consisting of 3D and 2D convolutions is designed to thoroughly exploit the spectral-spatial information in the high-frequency and low-frequency scales with low computational complexity. Furthermore, we devise a spectral-prior-based refinement module (SPRM) in the initial stage of feature extraction, which cannot only force the network to emphasize the most informative bands while suppressing the useless ones, but also alleviate the effects of the domain shift between the base and novel categories to learn a collaborative embedding mapping. Extensive experiment results on four benchmark data sets demonstrate that the proposed CMFSL can outperform the state-of-the-art methods with few-shot annotated samples. [ABSTRACT FROM AUTHOR]

Deep learning algorithms have obtained great success in semantic segmentation of very high-resolution (VHR) remote sensing images. Nevertheless, training these models generally requires a large amount of accurate pixel-wise annotations, which is very laborious and time-consuming to collect. To reduce the annotation burden, this paper proposes a consistency-regularized region-growing network (CRGNet) to achieve semantic segmentation of VHR remote sensing images with point-level annotations. The key idea of CRGNet is to iteratively select unlabeled pixels with high confidence to expand the annotated area from the original sparse points. However, since there may exist some errors and noises in the expanded annotations, directly learning from them may mislead the training of the network. To this end, we further propose the consistency regularization strategy, where a base classifier and an expanded classifier are employed. Specifically, the base classifier is supervised by the original sparse annotations, while the expanded classifier aims to learn from the expanded annotations generated by the base classifier with the region-growing mechanism. The consistency regularization is thereby achieved by minimizing the discrepancy between the predictions from both the base and the expanded classifiers. We find such a simple regularization strategy is yet very useful to control the quality of the region-growing mechanism. Extensive experiments on two benchmark datasets demonstrate that the proposed CRGNet significantly outperforms the existing state-of-the-art methods. Codes and pre-trained models are available online (https://github.com/YonghaoXu/CRGNet). [ABSTRACT FROM AUTHOR]

Reducing redundancy is crucial for improving the efficiency of video recognition models. An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods. However, existing dynamic methods focus on either temporal or spatial selection independently while neglecting a reality that the redundancies are usually spatial and temporal, simultaneously. Moreover, their selected content is usually cropped with fixed shapes (e.g., temporally-cropped frames, spatially-cropped patches), while the realistic distribution of informative content can be much more diverse. With these two insights, this paper proposes to integrate temporal and spatial selection into an Action Keypoint Network (AK-Net). From different frames and positions, AK-Net selects some informative points scattered in arbitrary-shaped regions as a set of “action keypoints” and then transforms the video recognition into point cloud classification. More concretely, AK-Net has two steps, i.e., the keypoint selection and the point cloud classification. First, it inputs the video into a baseline network and outputs a feature map from an intermediate layer. We view each pixel on this feature map as a spatial-temporal point and select some informative keypoints using self-attention. Second, AK-Net devises a ranking criterion to arrange the keypoints into an ordered 1D sequence. Since the video is represented with a 1D sequence after the specified layer, AK-Net transforms the subsequent layers into a point cloud classification sub-net by compacting the original 2D convolutional kernels into 1D kernels. Consequentially, AK-Net brings two-fold benefits for efficiency: The keypoint selection step collects informative content within arbitrary shapes and increases the efficiency for modeling spatial-temporal dependencies, while the point cloud classification step further reduces the computational cost by compacting the convolutional kernels. Experimental results show that AK-Net can consistently improve the efficiency and performance of baseline methods on several video recognition benchmarks. [ABSTRACT FROM AUTHOR]

Deep subspace learning is an important branch of self-supervised learning and has been a hot research topic in recent years, but current methods do not fully consider the individualities of temporal data and related tasks. In this paper, by transforming the individualities of motion capture data and segmentation task as the supervision, we propose the local self-expression subspace learning network. Specifically, considering the temporality of motion data, we use the temporal convolution module to extract temporal features. To implement the local validity of self-expression in temporal tasks, we design the local self-expression layer which only maintains the representation relations with temporally adjacent motion frames. To simulate the interpolatability of motion data in the feature space, we impose a group sparseness constraint on the local self-expression layer to impel the representations only using selected keyframes. Besides, based on the subspace assumption, we propose the subspace projection loss, which is induced from distances of each frame projected to the fitted subspaces, to penalize the potential clustering errors. The superior performances of the proposed model on the segmentation task of synthetic data and three tasks of real motion capture data demonstrate the feature learning ability of our model. [ABSTRACT FROM AUTHOR]

Serving as an essential step for many applications of image processing, superpixel generation has attracted a lot of attentions. Most existing superpixel generation algorithms focus on the boundary adherence and compactness of the superpixels, but ignore the topological consistency between the superpixels, which severely limites their applications in the subsequent tasks, especially in the CNN based image processing tasks. In this paper, we present a fast lattice superpixel generation algorithm, which can generate superpixels with lattice topology like the original pixels. We also propose a local similarity loss function to improve the segmentation accuracy of the generated lattice superpixels. The whole algorithm is parallelly implemented on GPU. We perform extensive experiments on three datasets (i.e., BSDS500, NYUv2 and VOC) to verify the efficacy of our algorithm. The experimental results show that our method achieves competitive results compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel multi-scale attention based network (called MSA-Net) for feature matching problems. Current deep networks based feature matching methods suffer from limited effectiveness and robustness when applied to different scenarios, due to random distributions of outliers and insufficient information learning. To address this issue, we propose a multi-scale attention block to enhance the robustness to outliers, for improving the representational ability of the feature map. In addition, we also design a novel context channel refine block and a context spatial refine block to mine the information context with less parameters along channel and spatial dimensions, respectively. The proposed MSA-Net is able to effectively infer the probability of correspondences being inliers with less parameters. Extensive experiments on outlier removal and relative pose estimation have shown the performance improvements of our network over current state-of-the-art methods with less parameters on both outdoor and indoor datasets. Notably, our proposed network achieves an 11.7% improvement at error threshold 5° without RANSAC than the state-of-the-art method on relative pose estimation task when trained on YFCC100M dataset. [ABSTRACT FROM AUTHOR]

Previous deep learning-based video stabilizers require a large scale of paired unstable and stable videos for training, which are difficult to collect. Traditional trajectory-based stabilizers, on the other hand, divide the task into several sub-tasks and tackle them subsequently, which are fragile in textureless and occluded regions regarding the usage of hand-crafted features. In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation power of DNNs to handle the challenges in real-world scenarios. Technically, DUT is composed of a trajectory estimation stage and a trajectory smoothing stage. In the trajectory estimation stage, we first estimate the motion of keypoints, initialize and refine the motion of grids via a novel multi-homography estimation strategy and a motion refinement network, respectively, and get the grid-based trajectories via temporal association. In the trajectory smoothing stage, we devise a novel network to predict dynamic smoothing kernels for trajectory smoothing, which can well adapt to trajectories with different dynamic patterns. We exploit the spatial and temporal coherence of keypoints and grid vertices to formulate the training objectives, resulting in an unsupervised training scheme. Experiment results on public benchmarks show that DUT outperforms state-of-the-art methods both qualitatively and quantitatively. The source code is available at https://github.com/Annbless/DUTCode. [ABSTRACT FROM AUTHOR]

Multi-focus image fusion (MFIF) attempts to achieve an “all-focused” image from multiple source images with the same scene but different focused objects. Given the lack of multi-focus image sets for network training, we propose a self-supervised residual feature learning model in this paper. The model consists of a feature extraction network and a fusion module. We select image super-resolution as a pretext task in the MFIF field, which is supported by a new residual gradient prior discovered by our theoretical study for low- and high-resolution (LR-HR) image pairs, as well as for multi-focus images. In the pretext task, our network’s training set is LR-HR image pairs generated from natural images, and HR images can be regarded as pseudo-labels of LR images. In the fusion task, the trained network extracts residual features of multi-focus images firstly. Secondly, the fusion module, consisting of an activity level measurement and a new boundary refinement method, is leveraged for the features to generated decision maps. Experimental results, both subjective evaluations and objective evaluations, demonstrate that our approach outperforms other state-of-the-art fusion algorithms. [ABSTRACT FROM AUTHOR]

Multiview video coding (MVC) aims to compress the multiview video through the elimination of video redundancies, where the quality of the reference frame directly affects the compression efficiency. In this paper, we propose a deep virtual reference frame generation method based on a disparity-aware reference frame generation network (DAG-Net) to transform the disparity relationship between different viewpoints and generate a more reliable reference frame. The proposed DAG-Net consists of a multi-level receptive field module, a disparity-aware alignment module, and a fusion reconstruction module. First, a multi-level receptive field module is designed to enlarge the receptive field, and extract the multi-scale deep features of the temporal and inter-view reference frames. Then, a disparity-aware alignment module is proposed to learn the disparity relationship, and perform disparity shift on the inter-view reference frame to align it with the temporal reference frame. Finally, a fusion reconstruction module is utilized to fuse the complementary information and generate a more reliable virtual reference frame. Experiments demonstrate that the proposed reference frame generation method achieves superior performance for multiview video coding. [ABSTRACT FROM AUTHOR]

We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor maps the learned representations to quality scores in a No-Reference (NR) setting. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models, even without any additional fine-tuning of the CNN backbone. The learned representations are highly robust and generalize well across images afflicted by either synthetic or authentic distortions. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets. The implementations used in this paper are available at https://github.com/pavancm/CONTRIQUE. [ABSTRACT FROM AUTHOR]

Due to the increased popularity of augmented and virtual reality experiences, the interest in capturing high-resolution real-world point clouds has never been higher. Loss of details and irregularities in point cloud geometry can occur during the capturing, processing, and compression pipeline. It is essential to address these challenges by being able to upsample a low Level-of-Detail (LoD) point cloud into a high LoD point cloud. Current upsampling methods suffer from several weaknesses in handling point cloud upsampling, especially in dense real-world photo-realistic point clouds. In this paper, we present a novel geometry upsampling technique, PU-Dense, which can process a diverse set of point clouds including synthetic mesh-based point clouds, real-world high-resolution point clouds, real-world indoor LiDAR scanned objects, as well as outdoor dynamically acquired LiDAR-based point clouds. PU-Dense employs a 3D multiscale architecture using sparse convolutional networks that hierarchically reconstruct an upsampled point cloud geometry via progressive rescaling and multiscale feature extraction. The framework employs a UNet type architecture that downscales the point cloud to a bottleneck and then upscales it to a higher level-of-detail (LoD) point cloud. PU-Dense introduces a novel Feature Extraction Unit that incorporates multiscale spatial learning by employing filters at multiple sampling rates and receptive fields. The architecture is memory efficient and is driven by a binary voxel occupancy classification loss that allows it to process high-resolution dense point clouds with millions of points during inference time. Qualitative and quantitative experimental results show that our method significantly outperforms the state-of-the-art approaches by a large margin while having much lower inference time complexity. We further test our dataset on high-resolution photo-realistic datasets. In addition, our method can handle noisy data well. We further show that our approach is memory efficient compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep self-expressiveness-based subspace clustering methods have demonstrated effectiveness. However, existing works only consider the attribute information to conduct the self-expressiveness, limiting the clustering performance. In this paper, we propose a novel adaptive attribute and structure subspace clustering network (AASSC-Net) to simultaneously consider the attribute and structure information in an adaptive graph fusion manner. Specifically, we first exploit an auto-encoder to represent input data samples with latent features for the construction of an attribute matrix. We also construct a mixed signed and symmetric structure matrix to capture the local geometric structure underlying data samples. Then, we perform self-expressiveness on the constructed attribute and structure matrices to learn their affinity graphs separately. Finally, we design a novel attention-based fusion module to adaptively leverage these two affinity graphs to construct a more discriminative affinity graph. Extensive experimental results on commonly used benchmark datasets demonstrate that our AASSC-Net significantly outperforms state-of-the-art methods. In addition, we conduct comprehensive ablation studies to discuss the effectiveness of the designed modules. The code is publicly available at https://github.com/ZhihaoPENG-CityU/AASSC-Net. [ABSTRACT FROM AUTHOR]

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios. [ABSTRACT FROM AUTHOR]

The practical task of Automatic Check-Out (ACO) is to accurately predict the presence and count of each product in an arbitrary product combination. Beyond the large-scale and the fine-grained nature of product categories as its main challenges, products are always continuously updated in realistic check-out scenarios, which is also required to be solved in an ACO system. Previous work in this research line almost depends on the supervisions of labor-intensive bounding boxes of products by performing a detection paradigm. While, in this paper, we propose a Self-Supervised Multi-Category Counting (S2MC2) network to leverage the point-level supervisions of products in check-out images to both lower the labeling cost and be able to return ACO predictions in a class incremental setting. Specifically, as a backbone, our S2MC2 is built upon a counting module in a class-agnostic counting fashion. Also, it consists of several crucial components including an attention module for capturing fine-grained patterns and a domain adaptation module for reducing the domain gap between single product images as training and check-out images as test. Furthermore, a self-supervised approach is utilized in S2MC2 to initialize the parameters of its backbone for better performance. By conducting comprehensive experiments on the large-scale automatic check-out dataset RPC, we demonstrate that our proposed S2MC2 achieves superior accuracy in both traditional and incremental settings of ACO tasks over the competing baselines. [ABSTRACT FROM AUTHOR]

The success of current deep saliency models heavily depends on large amounts of annotated human fixation data to fit the highly non-linear mapping between the stimuli and visual saliency. Such fully supervised data-driven approaches are annotation-intensive and often fail to consider the underlying mechanisms of visual attention. In contrast, in this paper, we introduce a model based on various cognitive theories of visual saliency, which learns visual attention patterns in a weakly supervised manner. Our approach incorporates insights from cognitive science as differentiable submodules, resulting in a unified, end-to-end trainable framework. Specifically, our model encapsulates the following important components motivated from biological vision. (a) As scene semantics are closely related to visually attentive regions, our model encodes discriminative spatial information for scene understanding through spatial visual semantics embedding. (b) To model the objectness factors in visual attention deployment, we incorporate object-level semantics embedding and object relation information. (c) Considering the “winner-take-all” mechanism in visual stimuli processing, we model the competition mechanism among objects with softmax based neural attention. (d) Lastly, a conditional center prior is learned to mimic the spatial distribution bias of visual attention. Furthermore, we propose novel loss functions to utilize supervision cues from image-level semantics, saliency prior knowledge, and self-information compression. Experiments show that our method achieves promising results, and even outperforms many of its fully supervised counterparts. Overall, our weakly supervised saliency method makes an essential step towards reducing the annotation budget of current approaches, as well as providing a more comprehensive understanding of the visual attention mechanism. Our code is available at: https://github.com/ashleylqx/WeakFixation.git. [ABSTRACT FROM AUTHOR]

Object detection is usually solved by learning a deep architecture involving classification and localization tasks, where feature learning for these two tasks is shared using the same backbone model. Recent works have shown that suitable disentanglement of classification and localization tasks has the great potential to improve performance of object detection. Despite the promising performance, existing feature disentanglement methods usually suffer from two limitations. First, most of them only focus on the disentangled proposals or predication heads for classification and localization tasks after RPN. While little consideration has been given to that the features for these two different tasks actually are obtained by a shared backbone model before RPN. Second, they are suggested for two-stage objectors and are not applicable to one-stage methods. To overcome these limitations, this paper presents a novel fully task-specific feature learning method for one-stage object detection. Specifically, our method first learns disentangled features for classification and localization tasks using two separated backbone models, where auxiliary classification and localization heads are inserted at the end of the two backbone models for providing a fully task-specific features for classification and localization. Then, a feature interaction module is developed for aligning and fusing task-specific features, which are further used to produce the final detection result. Experiments on MS COCO show that our proposed method (dubbed CrabNet) can achieve clear improvement over counterparts with increasing limited inference time, while performing favorably against state-of-the-arts. [ABSTRACT FROM AUTHOR]