Search

Raman spectroscopy is an effective method for diagnosing the aging state of transformer oil-paper insulation. Aiming at overcoming the drawback of previous methods that require a large number of training samples, this research proposes a method for aging diagnosis of oil-paper insulation that can be used for few-shot learning. In this study, different Raman spectroscopy samples of aging insulating oil are obtained by accelerated thermal aging experiments. This paper uses identity matrix as node feature, calculates the connection weights between them by Gaussian kernel function, and constructs the graph structure of Raman spectroscopy library. Using graph convolutional neural network (GCN) based on the graph structure, a diagnosis model is established. The diagnostic accuracy rate is as high as 95.5%. This method provides a theoretical basis for establishing a new structured Raman spectroscopy library and assessing the aging state of transformer oil-paper insulation with a small number of training samples. [ABSTRACT FROM AUTHOR]

Detecting insulation performance through testing the Raman spectroscopy of transformer oil is noninvasive and shows great promise in on-site diagnosis. The information, stored in spectra, that may reflect aging states of insulation aims to be effectively unfolded and provides decision support as well. In this article, a transformation method based on intrinsic product arithmetic is used to transform the 1-D Raman spectral data into 2-D image data. With the help of CNN based on the dimensionality expanding method, diagnosis of oil–paper insulation with different aging states based on the Raman spectroscopy was realized. The network-based oil–paper insulation aging diagnosis model has an accuracy of 95% in ten aging categories of 60 test samples and 100% in four aging categories. The result shows the trained CNN was able to identify the differences of transformer oil samples at each aging stage through visualized Raman spectral image. This method provides a more accurate determination method for diagnosing oil-immersed transformers’ aging conditions; it also develops an available method for a more detailed evaluation of insulation aging levels. [ABSTRACT FROM AUTHOR]

With the advantages of low power consumption, flexibility, and high readability against bright ambiance, electrophoretic displays (EPDs) have wide application prospects in the fields of education, smart supermarkets, Internet of Things, smart homes, wearable devices, etc. EPDs suffer from a severe history dependence during grayscale switching, which results in annoying ghost images. However, currently, it is difficult to distinguish diverse types of ghost images automatically; thus, lookup-tables (LUTs) for multi-grayscale waveform design cannot be effectively generated but require cumbersome manual adjustment. In this article, we proposed to adopt a convolutional neural network (CNN) to automatically recognize ghost images, based on which, LUTs that could suppress ghost images and achieve accurate grayscales were automatically generated for waveform design. Moreover, the workforce for manual adjustment was significantly saved. The results suggest that the CNN is a powerful tool for EPDs to achieve better image quality, as well as less manual cost. [ABSTRACT FROM AUTHOR]

The semiconductor industry is the core industry of the information age. As a key link in the semiconductor industry, wafer fabrication plays a key role in its development. In the testing stage of the wafer, each die of the wafer is detected and marked, and a wafer map with a certain spatial pattern can be formed. The analysis and classification of these spatial patterns can identify the cause of wafer defects, thereby improving production yield. However, as wafer size increases, line widths become smaller, etc., the probability of a mixed defect mode wafer pattern increases. Moreover, the mixed defect mode wafer map is more difficult to identify and classify than the single defect mode wafer map. Therefore, this paper proposes an improved deep convolutional neural network (DCNN) structure model for the recognition and classification of mixed defect pattern wafer maps. From the perspective of increasing the width of the DCNN, the improved network structure can avoid problems such as over-fitting and limited extraction of features due to the continuous deepening of the DCNN. The network is called Multi-Path DCNN (MP-DCNN) structure. The experimental results show that the proposed Multi-Path DCNN structure has better performance and higher classification accuracy than existing methods. [ABSTRACT FROM AUTHOR]

In the field of reversible data hiding (RDH), how to predict an image and embed a message into the image with smaller distortion are two important aspects. In this paper, we propose a novel and efficient RDH method by innovating an intelligent predictor and an adaptive embedding way. In the prediction stage, we first constructed a convolutional neural network (CNN) based predictor by reasonably dividing an image into four parts. In such a way, each part can be predicted by using the other three parts as the context for the improvement of the prediction performance. Compared with existing predictors, the proposed CNN predictor can use more neighboring pixels for the prediction by exploiting its multi-receptive fields and global optimization capacities. In the embedding stage, we also developed a prediction-error-ordering (PEO) based adaptive embedding strategy, which can better adapt image content and thus efficiently reduce the embedding distortion by elaborately and luminously applying background complexity to select and pair those smaller prediction errors for data hiding. With the proposed CNN prediction and embedding ways, the RDH method presented in this paper provides satisfactory results in improving the visual quality of data hidden images, e.g., the average PSNR value for the Kodak benchmark dataset can reach as high as 63.59 dB with an embedding capacity of 10,000 bits. Extensive experimental results have shown that the RDH method proposed in this paper is superior to those existing state-of-the-art works. [ABSTRACT FROM AUTHOR]

In this paper, the discrete wavelet transform (DWT) and a chaotic system were combined with a convolutional neural network (CNN) and applied to the diagnosis of insulation faults in XLPE (cross-linked polyacetylene) power cables. First, four different types of insulation faults in power cables were constructed, including the normal state of the cable, the short outer semi-conducting layer, impurities in the insulation layer, and insulation layer damage, and a high-speed capture card (NI PXI-5105) was adopted to measure the partial discharge (PD) signal, which was then filtered through discrete wavelet transform. Then, based on the Lorenz chaotic system, a dynamic error scatter diagram was established as the feature of each fault state. Finally, the dynamic error scatter diagram was processed by CNN to recognize four different types of faults in the power cable. The test results show that the method proposed in this paper can quickly recognize the fault state of power cables and has excellent performance in terms of recognition accuracy, which reaches 97.5%. Therefore, the proposed method can effectively detect the fault signal changes of power cables and identify the fault state of power cables in real time. [ABSTRACT FROM AUTHOR]

Radio signal recognition has a wide application in future communication systems and the vehicular communication, whose core is the extraction of signal features such as electromagnetic fingerprints. With the rapid development of artificial intelligence technology, deep learning has made amazing breakthroughs in image recognition, speech recognition and other fields. Deep learning is applied to electromagnetic fingerprint extraction in this paper. Firstly, thousands of the downlink aircraft communications addressing and reporting system (ACARS) signals used for communication between civil aircraft and airport tower are collected and generated. Then a pre-transformation network suitable for electromagnetic signals is constructed to convert one-dimensional signals into two-dimensional feature maps, and afterwards the feature maps are input into the convolutional neural network (CNN) for classification. By adopting the attention modules, the classification results were improved by a few percentage points over the baseline with a little cost. The method proposed in this paper achieves an accuracy rate of 94.1% and can obtain the aircraft type in a shorter time than traditional method. Moreover, the robustness of the proposed model in response to additive Gaussian white noise (AWGN) and phase deviation is studied and tested. [ABSTRACT FROM AUTHOR]

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

The new generation of the high-efficiency video coding (HEVC) video coding standard has improved compression performance and brought considerable coding complexity. Therefore, reducing the perception redundancy of video to obtain a better compression effect is the new direction of video development at present. In this paper, the HEVC is improved and enhanced from the aspects of a video saliency algorithm based on an attention mechanism and a video compression algorithm based on perception priority. In terms of video saliency, this paper proposes a spatial saliency algorithm based on a convolutional neural network and a temporal saliency algorithm based on motion vector. The saliency algorithm can combine the motion estimation results of each block during the HEVC compression on the basis of convolutional neural network and carry out adaptive dynamic fusion of the two, to complete the saliency map of the input video. In the aspect of the video compression algorithm with perception priority, this paper proposes a more flexible QP selection method, which selects its corresponding QP according to the saliency value of CU. At the same time, we propose a new rate-distortion optimization algorithm, which integrates the current block’s saliency feature into the traditional rate-distortion calculation method, to guide the allocation of bits and achieve the purpose of perception priority. The experimental results proved the superiority of the proposed method over the state-of-the-art perceptual coding algorithms in terms of saliency detection and perceptual compression quality. [ABSTRACT FROM AUTHOR]

With the rapid development of screen content video applications, screen content coding (SCC) is urgently needed to be used in commercial codecs. However, the extra encoding complexity introduced by the new SCC tools has posed a great challenge for its practical deployment. In this paper, motivated by our observations that there should be a fine-grained mapping between image content and candidate modes, we propose a two-step fast mode decision method to reduce the encoding complexity. First, we propose to use a convolution neural network (CNN) to automatically extract useful features for fine-grained content classification. Second, we build a precise and concise mapping from CUs to candidate modes by simultaneously considering CU content type, CU size, and mode complexity. Note that the spatial correlations between neighboring CUs and current CU are also utilized in candidate modes derivation. In addition to the two-step fast mode decision method, a content-aware early termination algorithm is further proposed to reduce the encoding complexity. Extensive experiments demonstrate that our method achieves better performance compared with state-of-the-art ones, with 50.13% total encoding complexity reduction and only 0.92% BD-rate increase. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) rely on satellite systems for stable positioning. However, due to limited satellite coverage or communication disruptions, UAVs may lose signals for positioning. In such situations, vision-based techniques can serve as an alternative, ensuring the self-positioning capability of UAVs. However, most of the existing datasets are developed for the geo-localization task of the objects captured by UAVs, rather than UAV self-positioning. Furthermore, the existing UAV datasets apply discrete sampling to synthetic data, such as Google Maps, neglecting the crucial aspects of dense sampling and the uncertainties commonly experienced in practical scenarios. To address these issues, this paper presents a new dataset, DenseUAV, that is the first publicly available dataset tailored for the UAV self-positioning task. DenseUAV adopts dense sampling on UAV images obtained in low-altitude urban areas. In total, over 27K UAV- and satellite-view images of 14 university campuses are collected and annotated. In terms of methodology, we first verify the superiority of Transformers over CNNs for the proposed task. Then we incorporate metric learning into representation learning to enhance the model’s discriminative capacity and to reduce the modality discrepancy. Besides, to facilitate joint learning from both the satellite and UAV views, we introduce a mutually supervised learning approach. Last, we enhance the Recall@K metric and introduce a new measurement, SDM@K, to evaluate both the retrieval and localization performance for the proposed task. As a result, the proposed baseline method achieves a remarkable Recall@1 score of 83.01% and an SDM@1 score of 86.50% on DenseUAV. The dataset and code have been made publicly available on https://github.com/Dmmm1997/DenseUAV. [ABSTRACT FROM AUTHOR]

Effectively evaluating the perceptual quality of dehazed images remains an under-explored research issue. In this paper, we propose a no-reference complex-valued convolutional neural network (CV-CNN) model to conduct automatic dehazed image quality evaluation. Specifically, a novel CV-CNN is employed that exploits the advantages of complex-valued representations, achieving better generalization capability on perceptual feature learning than real-valued ones. To learn more discriminative features to analyze the perceptual quality of dehazed images, we design a dual-stream CV-CNN architecture. The dual-stream model comprises a distortion-sensitive stream that operates on the dehazed RGB image, and a haze-aware stream on a novel dark channel difference image. The distortion-sensitive stream accounts for perceptual distortion artifacts, while the haze-aware stream addresses the possible presence of residual haze. Experimental results on three publicly available dehazed image quality assessment (DQA) databases demonstrate the effectiveness and generalization of our proposed CV-CNN DQA model as compared to state-of-the-art no-reference image quality assessment algorithms. [ABSTRACT FROM AUTHOR]

Versatile Video Coding (VVC) was finalized in 2020 and offered promising coding efficiency with a bitrate reduction of about 50% for same video quality as High Efficiency Video Coding. However, its high encoding complexity is a heavy burden on real-time applications. In particular, the very high complexity in intra coding can be a big barrier into market entry. This paper presents an efficient low-complexity intra coding scheme, which employs downsampling and upsampling processes. The downsampling is simply performed by reducing the resolution of an original video in both horizontal and vertical directions. In the upsampling, convolutional neural network based super-resolution is used to increase the resolution of the reconstructed video. In addition, this paper thoroughly analyzes the performance and complexity of all intra coding tools in VVC. Experimental results demonstrate that the significantly high reduction of the encoding complexity can be achieved with acceptable video quality. [ABSTRACT FROM AUTHOR]

The world of sports intrinsically involves fast and complex events that are difficult for coaches, trainers and players to analyze, and also for audiences to follow. In fast paced team sports such as soccer, keeping track of all the players and analyzing their performance after every match are very challenging. Current scenarios for identifying the best talents in soccer involve word-of-mouth and coaches/recruiters scouring through hours of manually annotated videos. This is a very expensive and laborious process and also biased by the nature of the recruiters. To alleviate these problems, this paper proposes an automated system that can detect, track, classify the teams of multiple players and identify the player controlling the ball in a video. The system generates three very important tactical statistics for a player: 1) duration of ball possession, 2) number of successful passes and 3) number of successful steals. This is done by training Convolutional Neural Networks (CNNs) to (a) localize and track the players on the field, (b) classify the team of a detected player, (c) identify the player controlling the ball and (d) pooling all the information extracted from (a), (b), and (c) to generate the statistics of players. To overcome the problem that the features learned from specific soccer matches do not necessarily generalize across different soccer matches, the paper proposes minimal amount of match-specific annotation and data augmentation, using a variant of Deep Convolutional Generative Adversarial Networks (DCGAN) to improve the accuracy. Experimental results and ablation studies show that the proposed approach outperforms the state-of-the-art approaches in terms of accuracy and processing speed. [ABSTRACT FROM AUTHOR]

This paper investigates the feasibility of novel data-driven deep learning (DL) models to predict the solution of Maxwell’s equations for low-frequency electromagnetic (EM) devices. With ground truth (empirical evidence) data being generated from a finite-element analysis solver, a deep convolutional neural network is trained in a supervised manner to learn a mapping for magnetic field distribution for topologies of different complexities of geometry, material, and excitation, including a simple coil, a transformer, and a permanent magnet motor. Preliminary experiments show DL model predictions in close agreement with the ground truth. A probabilistic model is introduced to improve the accuracy and to quantify the uncertainty in the prediction, based on Monte Carlo dropout. This paper establishes a basis for a fast and generalizable data-driven model used in the analysis, design, and optimization of EM devices. [ABSTRACT FROM AUTHOR]

This paper proposes a momentum algorithm based on Borges difference and an adaptive momentum (Adam) algorithm based on Borges difference to update parameters, which can adjust the momentum information more flexibly. The Borges difference is proposed from the definition of Borges derivative to be combined with the gradient algorithm in convolutional neural networks. The proposed momentum algorithm based on Borges difference and Adam algorithm based on Borges difference can be adjusted more flexibly in order to speed up the convergence. The parameter optimization algorithm with the Borges difference presents a better performance compared with the integer-order momentum algorithm and integer-order Adam algorithm, with the proposed nonlinear adjustment method for the parameter tuning of convolutional neural networks. By analyzing experimental results of Fashion-MNIST dataset and CIFAR-10 dataset, the optimization algorithms based on Borges difference proposed in this paper gain better effects on the optimization model compared with the corresponding ones based on the integer-order difference, and can speed up the convergence speed and recognition accuracy of the image recognition. [ABSTRACT FROM AUTHOR]

Musculoskeletal models have been widely used for detailed biomechanical analysis to characterise various functional impairments given their ability to estimate movement variables (i.e., muscle forces and joint moments) which cannot be readily measured in vivo. Physics-based computational neuromusculoskeletal models can interpret the dynamic interaction between neural drive to muscles, muscle dynamics, body and joint kinematics and kinetics. Still, such set of solutions suffers from slowness, especially for the complex models, hindering the utility in real-time applications. In recent years, data-driven methods have emerged as a promising alternative due to the benefits in speedy and simple implementation, but they cannot reflect the underlying neuromechanical processes. This paper proposes a physics-informed deep learning framework for musculoskeletal modelling, where physics-based domain knowledge is brought into the data-driven model as soft constraints to penalise/regularise the data-driven model. We use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework. Simultaneously, the physics law between muscle forces and joint kinematics is used the soft constraint. Experimental validations on two groups of data, including one benchmark dataset and one self-collected dataset from six healthy subjects, are performed. The experimental results demonstrate the effectiveness and robustness of the proposed framework. [ABSTRACT FROM AUTHOR]

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with $L$ L layers have $L$ L connections—one between each layer and its subsequent layer—our network has $\frac{L(L+1)}{2}$ L (L + 1) 2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, encourage feature reuse and substantially improve parameter efficiency. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less parameters and computation to achieve high performance. [ABSTRACT FROM AUTHOR]

The paper proposes a novel block-wise prediction paradigm based on Convolutional Neural Networks (CNNs) for lossless video coding. A deep neural network model which follows a multi-resolution design is employed for block-wise prediction. Several contributions are proposed to improve neural network training. A first contribution proposes a novel loss function formulation for an efficient network training based on a new approach for patch selection. Another contribution consists in replacing all HEVC-based angular intra-prediction modes with a CNN-based intra-prediction method, where each angular prediction mode is complemented by a CNN-based prediction mode using a specifically trained model. Another contribution consists in an efficient adaptation of the CNN-based intra-prediction residual for lossless video coding. Experimental results on standard test sequences show that the proposed coding system outperforms the HEVC standard with an average bitrate improvement of around 5%. To our knowledge, the paper is the first to replace all the traditional HEVC-based angular intra-prediction modes with an intra-prediction method based on modern Machine Learning techniques for lossless video coding applications. [ABSTRACT FROM AUTHOR]

This paper describes a video coding technology proposal submitted by MediaTek in April 2018 in response to a joint call for proposals (CfP) issued by ITU-T VCEG and ISO/IEC MPEG. The proposal uses the conventional block-based hybrid coding approach with a breakthrough design of block structure, substantial improvements of coding tools, and new inventions of loop filtering techniques. First, the block structure is designed using a highly flexible partitioning scheme, where each coding tree unit in a picture is split into multiple coding units (CUs) by a recursive quaternary tree followed by a recursive binary-ternary tree. The prediction unit (PU) and transform unit (TU) concepts are unified with the CU concept, i.e., PU and TU are basically the same as CU. Moreover, inter prediction, intra prediction, transform, quantization, in-loop filtering, and entropy coding are all improved. Finally, new loop filtering techniques are invented, where the proposed convolutional neural network loop filtering is of particular interest. The proposed video codec achieves 43.81% average bit rate savings based on objective measures compared to the High Efficiency Video Coding (HEVC) anchors and is among the best-performing CfP responses both objectively and subjectively. It has been partially adopted into the working draft of the Versatile Video Coding (VVC) standard. [ABSTRACT FROM AUTHOR]

This paper proposes a complex-valued convolutional neural network for land form classification and discovery in interferometric synthetic aperture radar (InSAR). Since the amount of satellite-borne SAR data has been increasing drastically, it is necessary to structurize the local features contained in observation data prior to utilization in the so-called big data framework for higher usability. Convolutional neural networks have such potential in general. However, there exists no network that can deal with complex amplitude data obtained in InSAR consistently. In this paper, we propose a complex-valued convolutional neural network to deal with InSAR. We demonstrate that the network classifies slopes and plains adaptively and, moreover, indicates small volcanos similar to a sample volcano (Omuroyama) included in the InSAR data. We also find their characteristic features emerging in the kernels in the convolution layers. These results reveal that the proposed complex-valued convolutional neural network is capable of successfully discovering unidentified lands similar to a prepared sample, which is highly useful for the InSAR data structurization. [ABSTRACT FROM AUTHOR]

In this paper, we present a method (Action-Fusion) for human action recognition from depth maps and posture data using convolutional neural networks (CNNs). Two input descriptors are used for action representation. The first input is a depth motion image that accumulates consecutive depth maps of a human action, whilst the second input is a proposed moving joints descriptor which represents the motion of body joints over time. In order to maximize feature extraction for accurate action classification, three CNN channels are trained with different inputs. The first channel is trained with depth motion images (DMIs), the second channel is trained with both DMIs and moving joint descriptors together, and the third channel is trained with moving joint descriptors only. The action predictions generated from the three CNN channels are fused together for the final action classification. We propose several fusion score operations to maximize the score of the right action. The experiments show that the results of fusing the output of three channels are better than using one channel or fusing two channels only. Our proposed method was evaluated on three public datasets: 1) Microsoft action 3-D dataset (MSRAction3D); 2) University of Texas at Dallas-multimodal human action dataset; and 3) multimodal action dataset (MAD) dataset. The testing results indicate that the proposed approach outperforms most of existing state-of-the-art methods, such as histogram of oriented 4-D normals and Actionlet on MSRAction3D. Although MAD dataset contains a high number of actions (35 actions) compared to existing action RGB-D datasets, this paper surpasses a state-of-the-art method on the dataset by 6.84%. [ABSTRACT FROM AUTHOR]

Image classification needs to consider the existence of image degradations in practice. Although degraded images have various levels of degradation, the degradation levels are usually unknown. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The proposed network can automatically infer ensemble weights by using estimated degradation levels of degraded images and features of restored images, where the degradation levels are estimated internally. The proposed network is mainly discussed with JPEG distortion, while degradations of both Gaussian noise and blurring are also examined. We demonstrate that the proposed network can classify degraded images over various levels of degradation. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images. [ABSTRACT FROM AUTHOR]

In underwater acoustic (UWA) adaptive communication system, due to time-varying channel, the transmitter often has outdated channel state information (CSI), which results in low efficiency. UWA channels are much more difficult to estimate and predict than terrestrial wireless channels, given the more severe multipath environments with varying propagation speeds in different locations, non-linear propagation paths, several-order higher propagation latency, mobile transceiver and obstacles in the sea, etc. To handle the complexity, this paper proposes an efficient online CSI prediction model for UWA CSI prediction considering the complicated correlationship of UWA channels in both the time and frequency domains. This paper designs a learning model called CsiPreNet, which is an integration of a one-dimensional convolutional neural network (CNN) and a long short term memory (LSTM) network. The performance is compared with the widely used recursive least squares (RLS) predictor, the approximate linear dependency recursive kernel least-squares (ALD-KRLS), and two common conventional deep neural networks (DNN) predictors, i.e., back propagation neural network (BPNN) and LSTM network using the measured data recorded in the South China Sea. To validate the efficacy of prediction, we investigate the prediction of CSI in simulated downlink UWA orthogonal frequency division multiple access (OFDMA) systems. Specifically, the measured UWA channel is used in the OFDMA system. A joint subcarrier-bit-power adaptive allocation scheme is used for resource allocation. To further improve the performance, we develop an offline-online prediction scheme, enabling the prediction results to be more stable. Simulation and experimental results show that the CsiPreNet has superior performance than the existing solutions, thanks to its capability in capturing both the temporal and frequency correlation of the UWA CSIs. [ABSTRACT FROM AUTHOR]

The articles in this special section focus on situation awareness in intelligent human-computer interaction for critical decision making (HCI). HCI is recognized as an ctive field that focuses on the various interactions of human with machines. The HCI has been widely applied in multiple domains, such as artificial intelligence, computer vision, image and multimedia analysis, and cognitive and behavioral sciences. The objective of the HCI is to make the computer smart via receiving enough knowledge about the environment where it is deployed and reduce the human intervention aspect toward decision making. This enables development of high-end computers that are context aware and smart in making decisions with reference to the context. Situation awareness of an intelligent HCI will decide the success and application of the solution across the real world environment. The aim of this special issue is to provide a platform on the topic of situation awareness in intelligent HCI for time critical decision making. [ABSTRACT FROM AUTHOR]

Owing to the limits of incident energy and hardware system, hyperspectral (HS) images always suffer from low spatial resolution, compared with multispectral (MS) or panchromatic (PAN) images. Therefore, image fusion has emerged as a useful technology that is able to combine the characteristics of high spectral and spatial resolutions of HS and PAN/MS images. In this paper, a novel HS and PAN image fusion method based on convolutional neural network (CNN) is proposed. The proposed method incorporates the ideas of both hyper-sharpening and MS pan-sharpening techniques, thereby employing a two-stage cascaded CNN to reconstruct the anticipated high-resolution HS image. Technically, the proposed CNN architecture consists of two sub-networks, the detail injection sub-network and unmixing sub-network. The former aims at producing a latent high-resolution MS image, whereas the latter estimates the desired high-resolution abundance maps by exploring the spatial and spectral information of both HS and MS images. Moreover, two model-training fashions are presented in this paper for the sake of effectively training our network. Experiments on simulated and real remote sensing data demonstrate that the proposed method can improve the spatial resolution and spectral fidelity of HS image, and achieve better performance than some state-of-the-art HS pan-sharpening algorithms. [ABSTRACT FROM AUTHOR]

The automatic detection and identification of fish from underwater videos is of great significance for fishery resource assessment and ecological environment monitoring. However, due to the poor quality of underwater images and unconstrained fish movement, traditional hand-designed feature extraction methods or convolutional neural network (CNN)-based object detection algorithms cannot meet the detection requirements in real underwater scenes. Therefore, to realize fish recognition and localization in a complex underwater environment, this paper proposes a novel composite fish detection framework based on a composite backbone and an enhanced path aggregation network called Composited FishNet. By improving the residual network (ResNet), a new composite backbone network (CBresnet) is designed to learn the scene change information (source domain style), which is caused by the differences in the image brightness, fish orientation, seabed structure, aquatic plant movement, fish species shape and texture differences. Thus, the interference of underwater environmental information on the object characteristics is reduced, and the output of the main network to the object information is strengthened. In addition, to better integrate the high and low feature information output from CBresnet, the enhanced path aggregation network (EPANet) is also designed to solve the insufficient utilization of semantic information caused by linear upsampling. The experimental results show that the average precision (AP)0.5:0.95, AP50 and average recall (AR)max=10 of the proposed Composited FishNet are 75.2%, 92.8% and 81.1%, respectively. The composite backbone network enhances the characteristic information output of the detected object and improves the utilization of characteristic information. This method can be used for fish detection and identification in complex underwater environments such as oceans and aquaculture. [ABSTRACT FROM AUTHOR]

The goal of image steganography is to hide a full-sized image, termed secret, into another, termed cover. Prior image steganography algorithms can conceal only one secret within one cover. In this paper, we propose an adaptive local image steganography (AdaSteg) system that allows for scale- and location-adaptive image steganography. By adaptively hiding the secret on a local scale, the proposed system makes the steganography more secured, and further enables multi-secret steganography within one single cover. Specifically, this is achieved via two stages, namely the adaptive patch selection stage and secret encryption stage. Given a pair of secret and cover, first, the optimal local patch for concealment is determined adaptively by exploiting deep reinforcement learning with the proposed steganography quality function and policy network. The secret image is then converted into a patch of encrypted noises, resembling the process of generating adversarial examples, which are further encoded to a local region of the cover to realize a more secured steganography. Furthermore, we propose a novel criterion for the assessment of local steganography, and also collect a challenging dataset that is specialized for the task of image steganography, thus contributing to a standardized benchmark for the area. Experimental results demonstrate that the proposed model yields results superior to the state of the art in both security and capacity. [ABSTRACT FROM AUTHOR]

Driven by the outstanding performance of neural networks in the structured euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each layer of the neural network as a parameterization to capture detail at the node level with a reduced number of parameters and computational complexity. Following this rationale, this paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. By extrapolating this strategy to more iterations between neighboring nodes, the EdgeNet learns edge- and neighbor-dependent weights to capture local detail. This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs). In writing different GNN architectures with a common language, EdgeNets highlight specific architecture advantages and limitations, while providing guidelines to improve their capacity without compromising their local implementation. For instance, we show that GCNNs have a parameter sharing structure that induces permutation equivariance. This can be an advantage or a limitation, depending on the application. In cases where it is a limitation, we propose hybrid approaches and provide insights to develop several other solutions that promote parameter sharing without enforcing permutation equivariance. Another interesting conclusion is the unification of GCNNs and GATs —approaches that have been so far perceived as separate. In particular, we show that GATs are GCNNs on a graph that is learned from the features. This particularization opens the doors to develop alternative attention mechanisms for improving discriminatory power. [ABSTRACT FROM AUTHOR]

Neural networks have achieved remarkable successes in machine learning tasks. This has recently been extended to graph learning using neural networks. However, there is limited theoretical work in understanding how and when they perform well, especially relative to established statistical learning techniques such as spectral embedding. In this short paper, we present a simple generative model where unsupervised graph convolutional network fails, while the adjacency spectral embedding succeeds. Specifically, unsupervised graph convolutional network is unable to look beyond the first eigenvector in certain approximately regular graphs, thus missing inference signals in non-leading eigenvectors. The phenomenon is demonstrated by visual illustrations and comprehensive simulations. [ABSTRACT FROM AUTHOR]

Knowledge distillation (KD) is a popular method to train efficient networks (“student”) with the help of high-capacity networks (“teacher”). Traditional methods use the teacher’s soft logits as extra supervision to train the student network. In this paper, we argue that it is more advantageous to make the student mimic the teacher’s features in the penultimate layer. Not only the student can directly learn more effective information from the teacher feature, feature mimicking can also be applied for teachers trained without a softmax layer. Experiments show that it can achieve higher accuracy than traditional KD. To further facilitate feature mimicking, we decompose a feature vector into the magnitude and the direction. We argue that the teacher should give more freedom to the student feature’s magnitude, and let the student pay more attention on mimicking the feature direction. To meet this requirement, we propose a loss term based on locality-sensitive hashing (LSH). With the help of this new loss, our method indeed mimics feature directions more accurately, relaxes constraints on feature magnitudes, and achieves state-of-the-art distillation accuracy. We provide theoretical analyses of how LSH facilitates feature direction mimicking, and further extend feature mimicking to multi-label recognition and object detection. [ABSTRACT FROM AUTHOR]

Movement intention inference for non-cooperative evasive targets in urban environments is difficult due to the lack of a priori knowledge of the possible target's movement intentions set. To solve this problem, this paper proposes a multi-level intention inference approach to construct and infer the movement intentions of a non-cooperative evasive target in urban environments. Firstly, to reasonably represent the possible movement intentions of the target, we decompose the target's movement intention into different regions at multiple levels according to the urban environment and the location of the target. At the same time, we divide the region at each level into several different sub-regions to represent the different movement intentions of the target at that level. Thus, the possible target's movement intentions are constructed as different regions at different levels where the target intends to go. Secondly, Convolutional Neural Network (CNN)-based intention inference models are developed, which can fuse the urban environment information and the observed target's trajectory to infer the target's movement intentions. Extensive simulation experiments results show that our proposed multi-level intention inference models can accurately and timely (with 79% accuracy and 84% timeliness) infer the region where the target intends to go when the possible destinations of the target are unknowable and maintain a robust inference performance when the target's behavior changes. [ABSTRACT FROM AUTHOR]

The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption. Efficient hardware architectures are under focused development to enable Artificial Intelligence (AI) at the resource-limited sensing devices. One of the most promising solutions is to enable Processing-in-Pixel (PIP) scheme. However, the conventional schemes suffer from the low fill-factor issue. This paper proposes a PIP based Complementary Metal-Oxide-Semiconductor (CMOS) sensor architecture, which allows convolution operation before the column readout circuit to significantly reduce the overall power consumption while improving the resource utilization of the succeeding deep learning accelerator. The simulation results show that the proposed architecture could support the computing efficiency up to 3.37 TOPS/W at the 8-bit weight configuration, which is four times as high as the conventional schemes after normalization. The transistors required for each pixel are only 3.5T, significantly improving the fill-factor. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) have demonstrated their ability to segment 2D cardiac ultrasound images. However, despite recent successes according to which the intra-observer variability on end-diastole and end-systole images has been reached, CNNs still struggle to leverage temporal information to provide accurate and temporally consistent segmentation maps across the whole cycle. Such consistency is required to accurately describe the cardiac function, a necessary step in diagnosing many cardiovascular diseases. In this paper, we propose a framework to learn the 2D+time apical long-axis cardiac shape such that the segmented sequences can benefit from temporal and anatomical consistency constraints. Our method is a post-processing that takes as input segmented echocardiographic sequences produced by any state-of-the-art method and processes it in two steps to (i) identify spatio-temporal inconsistencies according to the overall dynamics of the cardiac sequence and (ii) correct the inconsistencies. The identification and correction of cardiac inconsistencies relies on a constrained autoencoder trained to learn a physiologically interpretable embedding of cardiac shapes, where we can both detect and fix anomalies. We tested our framework on 98 full-cycle sequences from the CAMUS dataset, which are available alongside this paper. Our temporal regularization method not only improves the accuracy of the segmentation across the whole sequences, but also enforces temporal and anatomical consistency. [ABSTRACT FROM AUTHOR]

This paper tackles the problem of training a deep convolutional neural network of both low-bitwidth weights and activations. Optimizing a low-precision network is very challenging due to the non-differentiability of the quantizer, which may result in substantial accuracy loss. To address this, we propose three practical approaches, including (i) progressive quantization; (ii) stochastic precision; and (iii) joint knowledge distillation to improve the network training. First, for progressive quantization, we propose two schemes to progressively find good local minima. Specifically, we propose to first optimize a network with quantized weights and subsequently quantize activations. This is in contrast to the traditional methods which optimize them simultaneously. Furthermore, we propose a second progressive quantization scheme which gradually decreases the bitwidth from high-precision to low-precision during training. Second, to alleviate the excessive training burden due to the multi-round training stages, we further propose a one-stage stochastic precision strategy to randomly sample and quantize sub-networks while keeping other parts in full-precision. Finally, we adopt a novel learning scheme to jointly train a full-precision model alongside the low-precision one. By doing so, the full-precision model provides hints to guide the low-precision model training and significantly improves the performance of the low-precision network. Extensive experiments on various datasets (e.g., CIFAR-100, ImageNet) show the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

Multimodal, alias, guided, image restoration is the reconstruction of a degraded image from a target modality with the aid of a high quality image from another modality. A similar task is image fusion; it refers to merging images from different modalities into a composite image. Traditional approaches for multimodal image restoration and fusion include analytical methods that are computationally expensive at inference time. Recently developed deep learning methods have shown a great performance at a reduced computational cost; however, since these methods do not incorporate prior knowledge about the problem at hand, they result in a “black box” model, that is, one can hardly say what the model has learned. In this paper, we formulate multimodal image restoration and fusion as a coupled convolutional sparse coding problem, and adopt the Method of Multipliers (MM) for its solution. Then, we use the MM-based solution to design a convolutional neural network (CNN) encoder that follows the principle of deep unfolding. To address multimodal image restoration and fusion, we design two multimodal models which employ the proposed encoder followed by an appropriately designed decoder that maps the learned representations to the desired output. Unlike most existing deep learning designs comprising multiple encoding branches followed by a concatenation or a linear combination fusion block, the proposed design provides an efficient and structured way to fuse information at different stages of the network, providing representations that can lead to accurate image reconstruction. The proposed models are applied to three image restoration tasks, as well as two image fusion tasks. Quantitative and qualitative comparisons against various state-of-the-art analytical and deep learning methods corroborate the superior performance of the proposed framework. [ABSTRACT FROM AUTHOR]

Most deep learning models for temporal regression directly output the estimation based on single input images, ignoring the relationships between different images. In this paper, we propose deep relation learning for regression, aiming to learn different relations between a pair of input images. Four non-linear relations are considered: “cumulative relation,” “relative relation,” “maximal relation” and “minimal relation.” These four relations are learned simultaneously from one deep neural network which has two parts: feature extraction and relation regression. We use an efficient convolutional neural network to extract deep features from the pair of input images and apply a Transformer for relation learning. The proposed method is evaluated on a merged dataset with 6,049 subjects with ages of 0–97 years using 5-fold cross-validation for the task of brain age estimation. The experimental results have shown that the proposed method achieved a mean absolute error (MAE) of 2.38 years, which is lower than the MAEs of 8 other state-of-the-art algorithms with statistical significance (p<0.05) in paired T-test (two-side). [ABSTRACT FROM AUTHOR]

A lot of work has been done towards reconstructing the 3D facial structure from single images by capitalizing on the power of deep convolutional neural networks (DCNNs). In the recent works, the texture features either correspond to components of a linear texture space or are learned by auto-encoders directly from in-the-wild images. In all cases, the quality of the facial texture reconstruction is still not capable of modeling facial texture with high-frequency details. In this paper, we take a radically different approach and harness the power of generative adversarial networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images. That is, we utilize GANs to train a very powerful facial texture prior from a large-scale 3D texture dataset. Then, we revisit the original 3D Morphable Models (3DMMs) fitting making use of non-linear optimization to find the optimal latent parameters that best reconstruct the test image but under a new perspective. In order to be robust towards initialisation and expedite the fitting process, we propose a novel self-supervised regression based approach. We demonstrate excellent results in photorealistic and identity preserving 3D face reconstructions and achieve for the first time, to the best of our knowledge, facial texture reconstruction with high-frequency details. [ABSTRACT FROM AUTHOR]

In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization. Previous CNN quantization techniques tend to ignore the joint statistics of weights and activations, producing sub-optimal CNN performance at a given quantization bit-rate, or consider their joint statistics during training only and do not facilitate efficient compression of already trained CNN models. We optimally transform (decorrelate) and quantize the weights post-training using a rate–distortion framework to improve compression at any given quantization bit-rate. Transform quantization unifies quantization and dimensionality reduction (decorrelation) techniques in a single framework to facilitate low bit-rate compression of CNNs and efficient inference in the transform domain. We first introduce a theory of rate and distortion for CNN quantization and pose optimum quantization as a rate–distortion optimization problem. We then show that this problem can be solved using optimal bit-depth allocation following decorrelation by the optimal End-to-end Learned Transform (ELT) we derive in this paper. Experiments demonstrate that transform quantization advances the state of the art in CNN compression in both retrained and non-retrained quantization scenarios. In particular, we find that transform quantization with retraining is able to compress CNN models such as AlexNet, ResNet and DenseNet to very low bit-rates (1–2 bits). [ABSTRACT FROM AUTHOR]

This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Unlike previous practices that focus on exploring the embedding learning of foreground object (s), we consider background should be equally treated. Thus, we propose a Collaborative video object segmentation by Foreground-Background Integration (CFBI) approach. CFBI separates the feature embedding into the foreground object region and its corresponding background region, implicitly promoting them to be more contrastive and improving the segmentation results accordingly. Moreover, CFBI performs both pixel-level matching processes and instance-level attention mechanisms between the reference and the predicted sequence, making CFBI robust to various object scales. Based on CFBI, we introduce a multi-scale matching structure and propose an Atrous Matching strategy, resulting in a more robust and efficient framework, CFBI+. We conduct extensive experiments on two popular benchmarks, i.e., DAVIS and YouTube-VOS. Without applying any simulated data for pre-training, our CFBI+ achieves the performance ($\mathcal {J}$ J & $\mathcal {F}$ F ) of 82.9 and 82.8 percent, outperforming all the other state-of-the-art methods. Code: https://github.com/z-x-yang/CFBI. [ABSTRACT FROM AUTHOR]

Encoding-decoding (ED) CNNs have demonstrated state-of-the-art performance for noise reduction over the past years. This has triggered the pursuit of better understanding the inner workings of such architectures, which has led to the theory of deep convolutional framelets (TDCF), revealing important links between signal processing and CNNs. Specifically, the TDCF demonstrates that ReLU CNNs induce low-rankness, since these models often do not satisfy the necessary redundancy to achieve perfect reconstruction (PR). In contrast, this paper explores CNNs that do meet the PR conditions. We demonstrate that in these type of CNNs soft shrinkage and PR can be assumed. Furthermore, based on our explorations we propose the learned wavelet-frame shrinkage network, or LWFSN and its residual counterpart, the rLWFSN. The ED path of the (r)LWFSN complies with the PR conditions, while the shrinkage stage is based on the linear expansion of thresholds proposed Blu and Luisier. In addition, the LWFSN has only a fraction of the training parameters (<1%) of conventional CNNs, very small inference times, low memory footprint, while still achieving performance close to state-of-the-art alternatives, such as the tight frame (TF) U-Net and FBPConvNet, in low-dose CT denoising. [ABSTRACT FROM AUTHOR]

Online fault detection of insulators is a necessary requirement for the development of a smart grid, which directly affects the safety and reliability of power system operations. Breakage is an important factor causing insulator abnormalities, and a large number of image samples are often required for training to complete defect identification with the help of AI deep learning. In this paper, we propose a convolutional neural network ensemble implemented using small samples, data augmentation and transfer learning for insulator breakage detection. We used data augmentation to expand the small sample of 200 insulator images by 15 times to 3000 images, built a VGG16 transfer network, pre-trained the VGG16 network convolutional basis weights, and improved the training performance and efficiency of the model with freeze training and fine-tuning training. The training on 2700 images and testing results on 300 images show that the proposed method can achieve an accuracy of 0.9871 for insulator breakage recognition. [ABSTRACT FROM AUTHOR]

This paper presents a deep learning-based method for defect detection and classification of power distribution lines using video analysis. The first stage is dataset preparation in which different videos are recorded by a CoroCam 6D2 camera from distribution lines and labeled based on the defect type and the severity level of the defect. Then, a process is followed in such a way that a limited number of frames are used for processing, and power devices are detected in each frame using Faster R-CNN. The detector performance is improved by increasing the training dataset and changing the training hyper-parameters. Next, an equipment tracking technique is applied through the video frames. In the following, a method based on the classification of power equipment is presented. In this method, by corona color thresholding in all frames and applying a median filter over time, the connected components representing the corona are identified. Then, the frame containing the closest component to the component in the median image is selected. In the selected frame, the area around the component is cut and given to AlexNet or GoogleNet to determine the equipment type and the severity level of defect is determined. Also, the defective equipment phase is determined based on the insulators detected in the video. The proposed method not only performs better than the state-of-the-art but also is a practical method, and with the least dependence on environmental conditions, can automatically identify defects in distribution lines, even in videos containing several possible defective devices. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose $\Pi$ Π -Nets, a new class of function approximators based on polynomial expansions. $\Pi$ Π -Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that $\Pi$ Π -Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, $\Pi$ Π -Nets produce state-of-the-art results in three challenging tasks, i.e., image generation, face verification and 3D mesh representation learning. The source code is available at https://github.com/grigorisg9gr/polynomial_nets. [ABSTRACT FROM AUTHOR]

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose a deep feature-based text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms and the state-of-the-art pretrained language model, i.e., BERT, on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. [ABSTRACT FROM AUTHOR]

This paper presents a novel methodology to design a secured custom reusable intellectual property (IP) core for the convolutional layer of convolutional neural network (CNN). Since the reusable IP cores used in system-on-chips (SoCs) of consumer electronics (CE) systems are susceptible to the hardware threat of IP counterfeiting. Therefore, this paper also presents the security of the proposed convolutional layer reusable IP core against the threat of IP counterfeiting using facial biometrics. This enables the integration of secured reusable IP cores in the SoCs of CE systems, thereby ensuring the safety of end consumers. In the proposed approach, the convolutional layer IP core is designed through high-level synthesis (HLS) process and secured by embedding secret biometric security information into the design during register allocation phase of the HLS process. The qualitative and quantitative analysis of the proposed approach exhibits significantly lower probability of coincidence (Pc) (up to 47% less) and higher tamper tolerance (1.93E+25) than recent approaches. Further, it offers robust security with zero design overhead. [ABSTRACT FROM AUTHOR]

Due to the strong penetration ability and high transmission rate of ultra-wideband (UWB) signals, UWB technology plays a very significant role in the field of precise indoor positioning. However, the harsh and volatile indoor environment leads to non-line-of-sight (NLOS) propagation and severe attenuation of UWB signals, which may generate significant ranging and positioning errors. To mitigate NLOS effect and improve positioning accuracy, existing methods use ranging information and channel impulse response (CIR) to identify UWB signal propagation channels. However, these NLOS identification methods often require a priori knowledge and suitable thresholds, and most of them only perform a binary classification between LOS and NLOS in a particular scenario. To address these disadvantages, this paper proposes a novel multi-classification method to classify UWB signal propagation channels based on one-dimensional wavelet packet analysis (ODWPA) and convolutional neural network (CNN). This method first decomposes the CIR of known categories into colored coefficients images using a one-dimensional wavelet packet function, then uses these images to train CNNs with different structures, and finally selects CNN model with the best performance to identify the unknown category of UWB signal propagation channels. The experimental results show that the performance of the proposed method is always the best, regardless of the type of experimental scenario, and the identification accuracy is always higher than 90% and up to 100%. [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]

Over the past few years, deep convolutional neural network-based methods have made great progress in semantic segmentation of street scenes. Some recent methods align feature maps to alleviate the semantic gap between them and achieve high segmentation accuracy. However, they usually adopt the feature alignment modules with the same network configuration in the decoder and thus ignore the different roles of stages of the decoder during feature aggregation, leading to a complex decoder structure. Such a manner greatly affects the inference speed. In this paper, we present a novel Stage-aware Feature Alignment Network (SFANet) based on the encoder-decoder structure for real-time semantic segmentation of street scenes. Specifically, a Stage-aware Feature Alignment module (SFA) is proposed to align and aggregate two adjacent levels of feature maps effectively. In the SFA, by taking into account the unique role of each stage in the decoder, a novel stage-aware Feature Enhancement Block (FEB) is designed to enhance spatial details and contextual information of feature maps from the encoder. In this way, we are able to address the misalignment problem with a very simple and efficient multi-branch decoder structure. Moreover, an auxiliary training strategy is developed to explicitly alleviate the multi-scale object problem without bringing additional computational costs during the inference phase. Experimental results show that the proposed SFANet exhibits a good balance between accuracy and speed for real-time semantic segmentation of street scenes. In particular, based on ResNet-18, SFANet respectively obtains 78.1% and 74.7% mean of class-wise Intersection-over-Union (mIoU) at inference speeds of 37 FPS and 96 FPS on the challenging Cityscapes and CamVid test datasets by using only a single GTX 1080Ti GPU. [ABSTRACT FROM AUTHOR]

Hyperspectral image produces high spectral resolution at the sacrifice of spatial resolution. Without reducing the spectral resolution, improving the resolution in the spatial domain is a very challenging problem. Motivated by the discovery that hyperspectral image exhibits high similarity between adjacent bands in a large spectral range, in this paper, we explore a new structure for hyperspectral image super-resolution (DualSR), leading to a dual-stage design, i.e., coarse stage and fine stage. In coarse stage, five bands with high similarity in a certain spectral range are divided into three groups, and the current band is guided to study the potential knowledge. Under the action of alternative spectral fusion mechanism, the coarse SR image is super-resolved in band-by-band. In order to build model from a global perspective, an enhanced back-projection method via spectral angle constraint is developed in fine stage to learn the content of spatial-spectral consistency, dramatically improving the performance gain. Extensive experiments demonstrate the effectiveness of the proposed coarse stage and fine stage. Besides, our network produces state-of-the-art results against existing works in terms of spatial reconstruction and spectral fidelity. Our code is publicly available at https://github.com/qianngli/DualSR. [ABSTRACT FROM AUTHOR]