Search

We study a very challenging task, human image completion, which tries to recover the human body part with a reasonable human shape from the corrupted region. Since each human body part is unique, it is infeasible to restore the missing part by borrowing textures from other visible regions. Thus, we propose two types of learned priors to compensate for the damaged region. One is a structure prior, it uses a human parsing map to represent the human body structure. The other is a structure-texture correlation prior. It learns a structure and a texture memory bank, which encodes the common body structures and texture patterns, respectively. With the aid of these memory banks, the model could utilize the visible pattern to query and fetch a similar structure and texture pattern to introduce additional reasonable structures and textures for the corrupted region. Besides, since multiple potential human shapes are underlying the corrupted region, we propose multi-scale structure discriminators to further restore a plausible topological structure. Experiments on various large-scale benchmarks demonstrate the effectiveness of our proposed method.

We propose an end-to-end method for simultaneously detecting local junctions and global wireframe in man-made environment. Our pipeline consists of an anchor-free junction detection module, a distance map learning module, and a line segment proposing and verification module. A set of line segments are proposed from the predicted junctions with guidance of the learned distance map, and further verified by the proposal verification module. Experimental results show that our method outperforms the previous state-of-the-art wireframe parser by a descent margin. In terms of line segments detection, our method shows competitive performance on standard benchmarks. The proposed networks are end-to-end trainable and efficient.aaThe code will be released on github for reproduction of the results.

Motivated by the correlation between the depth and the geometric structure of a 360 indoor image, we propose a novel learning-based depth estimation framework that leverages the geometric structure of a scene to conduct depth estimation. Specifically, we represent the geometric structure of an indoor scene as a collection of corners, boundaries and planes. On the one hand, once a depth map is estimated, this geometric structure can be inferred from the estimated depth map; thus, the geometric structure functions as a regularizer for depth estimation. On the other hand, this estimation also benefits from the geometric structure of a scene estimated from an image where the structure functions as a prior. However, furniture in indoor scenes makes it challenging to infer geometric structure from depth or image data. An attention map is inferred to facilitate both depth estimation from features of the geometric structure and also geometric inferences from the estimated depth map. To validate the effectiveness of each component in our framework under controlled conditions, we render a synthetic dataset, Shanghaitech-Kujiale Indoor 360 dataset with 3550 360 indoor images. Extensive experiments on popular datasets validate the effectiveness of our solution. We also demonstrate that our method can also be applied to counterfactual depth.

Diabetic retinopathy (DR), as a leading ocular disease, is often with a complication of diabetic macular edema (DME). However, most existing works only aim at DR grading but ignore the DME diagnosis, but doctors will do both tasks simultaneously. In this paper, motivated by the advantages of multi-task learning for image classification, and to mimic the behavior of clinicians in visual inspection for patients, we propose a feature Separation and Union Network (SUNet) for simultaneous DR and DME grading. Further, to improve the interpretability of the disease grading, a lesion regularizer is also imposed to regularize our network. Specifically, given an image, our SUNet first extracts a common feature for both DR and DME grading and lesion detection. Then a feature blending block is introduced which alternately uses feature separation and feature union for task-specific feature extraction, where feature separation learns task-specific features for lesion detection and DR and DME grading, and feature union aggregates features corresponding to lesion detection, DR and DME grading. In this way, we can distill the irrelevant features and leverage features of different but related tasks to improve the performance of each given task. Then the task-specific features of the same task at different feature separation steps are concatenated for the prediction of each task. Extensive experiments on the very challenging IDRiD dataset demonstrate that our SUNet significantly outperforms existing methods for both DR and DME grading.

Due to new eye diseases discovered every year, doctors may encounter some rare or unknown diseases. Similarly, in medical image recognition field, many practical medical classification tasks may encounter the case where some testing samples belong to some rare or unknown classes that have never been observed or included in the training set, which is termed as an open-set problem. As rare diseases samples are difficult to be obtained and included in the training set, it is reasonable to design an algorithm that recognizes both known and unknown diseases. Towards this end, this paper leverages a novel generative adversarial network (GAN) based synthetic learning for open-set retinal optical coherence tomography (OCT) image recognition. Specifically, we first train an auto-encoder GAN and a classifier to reconstruct and classify the observed images, respectively. Then a subspace-constrained synthesis loss is introduced to generate images that locate near the boundaries of the subspace of images corresponding to each observed disease, meanwhile, these images cannot be classified by the pre-trained classifier. In other words, these synthesized images are categorized into an unknown class. In this way, we can generate images belonging to the unknown class, and add them into the original dataset to retrain the classifier for the unknown disease discovery.

We propose a new learning paradigm, Local to Global Learning (LGL), for Deep Neural Networks (DNNs) to improve the performance of classification problems. The core of LGL is to learn a DNN model from fewer categories (local) to more categories (global) gradually within the entire training set. LGL is most related to the Self-Paced Learning (SPL) algorithm but its formulation is different from SPL. SPL trains its data from simple to complex, while LGL from local to global. In this paper, we incorporate the idea of LGL into the learning objective of DNNs and explain why LGL works better from an information-theoretic perspective. Experiments on the toy data, CIFAR-10, CIFAR-100, and ImageNet dataset show that LGL outperforms the baseline and SPL-based algorithms.

To simultaneously estimate head counts and localize heads with bounding boxes, a regression guided detection network (RDNet) is proposed for RGB-D crowd counting. Specifically, to improve the robustness of detection-based approaches for small/tiny heads, we leverage density map to improve the head/non-head classification in detection network where density map serves as the probability of a pixel being a head. A depth-adaptive kernel that considers the variances in head sizes is also introduced to generate high-fidelity density map for more robust density map regression. Further, a depth-aware anchor is designed for better initialization of anchor sizes in detection framework. Then we use the bounding boxes whose sizes are estimated with depth to train our RDNet. The existing RGB-D datasets are too small and not suitable for performance evaluation on data-driven based approaches, we collect a large-scale RGB-D crowd counting dataset. Experiments on both our RGB-D dataset and the MICC RGB-D counting dataset show that our method achieves the best performance for RGB-D crowd counting and localization. Further, our method can be readily extended to RGB image based crowd counting and achieves comparable performance on the ShanghaiTech Part\_B dataset for both counting and localization.

Pedestrian trajectory prediction is a challenging task because of the complex nature of humans. In this paper, we tackle the problem within a deep learning framework by considering motion information of each pedestrian and its interaction with the crowd. Specifically, motivated by the residual learning in deep learning, we propose to predict displacement between neighboring frames for each pedestrian sequentially. To predict such displacement, we design a crowd interaction deep neural network (CIDNN) which considers the different importance of different pedestrians for the displacement prediction of a target pedestrian. Specifically, we use an LSTM to model motion information for all pedestrians and use a multi-layer perceptron to map the location of each pedestrian to a high dimensional feature space where the inner product between features is used as a measurement for the spatial affinity between two pedestrians. Then we weight the motion features of all pedestrians based on their spatial affinity to the target pedestrian for location displacement prediction. Extensive experiments on publicly available datasets validate the effectiveness of our method for trajectory prediction.

Face aging is of great importance for cross-age recognition and entertainment related applications. However, the lack of labeled faces of the same person across a long age range makes it challenging. Because of different aging speed of different persons, our face aging approach aims at synthesizing a face whose target age lies in some given age group instead of synthesizing a face with a certain age. By grouping faces with target age together, the objective of face aging is equivalent to transferring aging patterns of faces within the target age group to the face whose aged face is to be synthesized. Meanwhile, the synthesized face should have the same identity with the input face. Thus we propose an Identity-Preserved Conditional Generative Adversarial Networks (IPCGANs) framework, in which a Conditional Generative Adversarial Networks module functions as generating a face that looks realistic and is with the target age, an identity-preserved module preserves the identity information and an age classifier forces the generated face with the target age. Both qualitative and quantitative experiments show that our method can generate more realistic faces in terms of image quality, person identity and age consistency with human observations.

This paper explores gaze prediction in dynamic 360° immersive videos, i.e., based on the history scan path and VR contents, we predict where a viewer will look at an upcoming time. To tackle this problem, we first present the large-scale eye-tracking in dynamic VR scene dataset. Our dataset contains 208 360° videos captured in dynamic scenes, and each video is viewed by at least 31 subjects. Our analysis shows that gaze prediction depends on its history scan path and image contents. In terms of the image contents, those salient objects easily attract viewers' attention. On the one hand, the saliency is related to both appearance and motion of the objects. Considering that the saliency measured at different scales is different, we propose to compute saliency maps at different spatial scales: the sub-image patch centered at current gaze point, the sub-image corresponding to the Field of View (FoV), and the panorama image. Then we feed both the saliency maps and the corresponding images into a Convolutional Neural Network (CNN) for feature extraction. Meanwhile, we also use a Long-Short-Term-Memory (LSTM) to encode the history scan path. Then we combine the CNN features and LSTM features for gaze displacement prediction between gaze point at a current time and gaze point at an upcoming time. Extensive experiments validate the effectiveness of our method for gaze prediction in dynamic VR scenes.

In this paper, we propose a learning-based approach to the task of automatically extracting a "wireframe" representation for images of cluttered man-made environments. The wireframe (see Fig. 1) contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. The data and source code are available at https://github.com/huangkuns/wireframe., CVPR 2018

Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighbouring frames be encoded with similar reconstruction coefficients. Then we map the TSC with a special type of stacked Recurrent Neural Network (sRNN). By taking advantage of sRNN in learning all parameters simultaneously, the nontrivial hyper-parameter selection to TSC can be avoided, meanwhile with a shallow sRNN, the reconstruction coefficients can be inferred within a forward pass, which reduces the computational cost for learning sparse coefficients. The contributions of this paper are two-fold: i) We propose a TSC, which can be mapped to a sRNN which facilitates the parameter optimization and accelerates the anomaly prediction. ii) We build a very large dataset which is even larger than the summation of all existing dataset for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset and real datasets demonstrate that our TSC based and sRNN based method consistently outperform existing methods, which validates the effectiveness of our method.

This paper tackles anomaly detection in videos, which is an extremely challenging task because anomaly is unbounded. We approach this task by leveraging a Convolutional Neural Network (CNN or ConvNet) for appearance encoding for each frame, and leveraging a Convolutional Long Short Term Memory (ConvLSTM) for memorizing all past frames which corresponds to the motion information. Then we integrate ConvNet and ConvLSTM with Auto-Encoder, which is referred to as ConvLSTM-AE, to learn the regularity of appearance and motion for the ordinary moments. Compared with 3D Convolutional Auto-Encoder based anomaly detection, our main contribution lies in that we propose a ConvLSTM-AE framework which better encodes the change of appearance and motion for normal events, respectively. To evaluate our method, we first conduct experiments on a synthesized Moving-MNIST dataset under controlled settings, and results show that our method can easily identify the change of appearance and motion. Extensive experiments on real anomaly datasets further validate the effectiveness of our method for anomaly detection.

© 2017 IEEE. Deep learning methods achieve great success recently on many computer vision problems. In spite of these practical successes, optimization of deep networks remains an active topic in deep learning research. In this work, we focus on investigation of the network solution properties that can potentially lead to good performance. Our research is inspired by theoretical and empirical results that use orthogonal matrices to initialize networks, but we are interested in investigating how orthogonal weight matrices perform when network training converges. To this end, we propose to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieve this by a simple yet effective method called Singular Value Bounding (SVB). In SVB, all singular values of each weight matrix are simply bounded in a narrow band around the value of 1. Based on the same motivation, we also propose Bounded Batch Normalization (BBN), which improves Batch Normalization by removing its potential risk of ill-conditioned layer transform. We present both theoretical and empirical results to justify our proposed methods. Experiments on benchmark image classification datasets show the efficacy of our proposed SVB and BBN. In particular, we achieve the state-of-the-art results of 3.06% error rate on CIFAR10 and 16.90% on CIFAR100, using off-the-shelf network architectures (Wide ResNets). Our preliminary results on ImageNet also show the promise in large-scale learning. We release the implementation code of our methods at www.aperture-lab.net/research/svb.

In this paper, we present a novel image codec by leveraging sparse representation strategy for geometric pattern encoding. Specifically, we propose a Multiple Learned Geometric Dictionaries (MLGD) solution to explore various texture patterns of images, and use different dictionaries to encode homogenous smooth components and heterogeneous directional components. Profiting from model proficiency, our approach better preserves subtle details with high expressiveness and eliminates artifacts such as ringing and blurring. Experimental results indicate the proposed codec outperforms state-of-the-art in both numerical measures and visual fidelity, lifting the quality of experience (QoE) at low bit-rate.

This paper aims to develop a method than can accurately estimate the crowd count from an individual image with arbitrary crowd density and arbitrary perspective. To this end, we have proposed a simple but effective Multi-column Convolutional Neural Network (MCNN) architecture to map the image to its crowd density map. The proposed MCNN allows the input image to be of arbitrary size or resolution. By utilizing filters with receptive fields of different sizes, the features learned by each column CNN are adaptive to variations in people/head size due to perspective effect or image resolution. Furthermore, the true density map is computed accurately based on geometry-adaptive kernels which do not need knowing the perspective map of the input image. Since exiting crowd counting datasets do not adequately cover all the challenging situations considered in our work, we have collected and labelled a large new dataset that includes 1198 images with about 330,000 heads annotated. On this challenging new dataset, as well as all existing datasets, we conduct extensive experiments to verify the effectiveness of the proposed model and method. In particular, with the proposed simple MCNN model, our method outperforms all existing methods. In addition, experiments show that our model, once trained on one dataset, can be readily transferred to a new dataset.

Fine grained video action analysis often requires reliable detection and tracking of various interacting objects and human body parts, denoted as Interactional Object Parsing. However, most of the previous methods based on either independent or joint object detection might suffer from high model complexity and challenging image content, e.g., illumination/pose/appearance/scale variation, motion, and occlusion etc. In this work, we propose an end-to-end system based on recurrent neural network to perform frame by frame interactional object parsing, which can alleviate the difficulty through an incremental/progressive manner. Our key innovation is that: instead of jointly outputting all object detections at once, for each frame we use a set of long-short term memory (LSTM) nodes to incrementally refine the detections. After passing through each LSTM node, more object detections are consolidated and thus more contextual information could be utilized to localize more difficult objects. The object parsing results are further utilized to form object specific action representation for fine grained action detection. Extensive experiments on two benchmark fine grained activity datasets demonstrate that our proposed algorithm achieves better interacting object detection performance, which in turn boosts the action recognition performance over the state-of-the-art.

RGB-D object recognition is an important research topic in computer version, and seeking a robust image representation is the most important sub problem for RGB-D object recognition. On the one hand, the recently emerging deep learning methods, which learns image representations automatically by capturing the data structure, have demonstrated the impressive performance for object recognition. On the other hand, the previously commonly used hand-crafted features also encodes the prior knowledge about the data. By realizing that the hand-crafted features and machine learnt features actually characterize the different aspects of image data, rather than only using one type of feature, we propose to jointly use the machine learnt features and hand-crafted features for RGB-D object recognition. Specifically, we use the Convolution Neural Networks (CNNs) to extract the machine learnt representation, and use Locality-constrained Linear Coding (LLC) based spatial pyramid matching for hand-crafted features. We evaluated our proposed approach on three publicly available RGB-D datasets. Experimental results show that our method achieves the best performance under all the cases, which demonstrates the effectiveness of our method.

We study in this paper the problem of learning classifiers from ambiguously labeled images. For instance, in the collection of new images, each image contains some samples of interest (\emph{e.g.,} human faces), and its associated caption has labels with the true ones included, while the sample-label association is unknown. The task is to learn classifiers from these ambiguously labeled images and generalize to new images. An essential consideration here is how to make use of the information embedded in the relations between samples and labels, both within each image and across the image set. To this end, we propose a novel framework to address this problem. Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image. If we can identify samples of the same class from each image and associate them across the image set, the matrix formed by the samples from the same class would be ideally low-rank. By leveraging such a low-rank assumption, we can simultaneously optimize a partial permutation matrix (PPM) for each image, which is formulated in order to exploit all information between samples and labels in a principled way. The obtained PPMs can be readily used to assign labels to samples in training images, and then a standard SVM classifier can be trained and used for unseen data. Experiments on benchmark datasets show the effectiveness of our proposed method.

We present a multi-layer group sparse coding framework for concurrent image classification and annotation. By leveraging the dependency between image class label and tags, we introduce a multi-layer group sparse structure of the reconstruction coefficients. Such structure fully encodes the mutual dependency between the class label, which describes the image content as a whole, and tags, which describe the components of the image content. Then we propose a multi-layer group based tag propagation method, which combines the class label and subgroups of instances with similar tag distribution to annotate test images. Moreover, we extend our multi-layer group sparse coding in the Reproducing Kernel Hilbert Space (RKHS) which captures the nonlinearity of features, and further improves performances of image classification and annotation. Experimental results on the LabelMe, UIUC-Sport and NUS-WIDE-Object databases show that our method outperforms the baseline methods, and achieves excellent performances in both image classification and annotation tasks.

Sparse coding which encodes the original signal in a sparse signal space, has shown its state-of-the-art performance in the visual codebook generation and feature quantization process of BoW based image representation. However, in the feature quantization process of sparse coding, some similar local features may be quantized into different visual words of the codebook due to the sensitiveness of quantization. In this paper, to alleviate the impact of this problem, we propose a Laplacian sparse coding method, which will exploit the dependence among the local features. Specifically, we propose to use histogram intersection based kNN method to construct a Laplacian matrix, which can well characterize the similarity of local features. In addition, we incorporate this Laplacian matrix into the objective function of sparse coding to preserve the consistence in sparse representation of similar local features. Comprehensive experimental results show that our method achieves or outperforms existing state-of-the-art results, and exhibits excellent performance on Scene 15 data set.

Current large scale image retrieval engines rely heavily on the surrounding text information, which inevitably includes some irrelevant images in the retrieval results due to the noisy environment. To improve the retrieval performance, we propose an unsupervised web image re-ranking method by incorporating images' visual information. Our method can automatically select a set of representative images from the original image pool as concept model, which is highly related to the query concept and critically important for the re-ranking result. With a similarity graph constructed by top results given by text based retrieval, we utilize Normalized Cut to select the part with the highest similarity density as concept model. We re-rank the rest images according to their similarities to the concept model. The advantages of our method are (i): Our method is unsupervised, and it doesn't need any pre-prepared query/training image or user's feedback, Thus it greatly facilitates users' retrieval. (ii): By finding a set of images rather than single image, we are able to give a more complete and more robust model for the query concept. (iii): Multi-ranking Integration Strategy is adopted to re-rank the rest images. Experiments show that our method can achieve satisfying results.