Research papers and code for "Yao Zhao":
We consider a requester who acquires a set of data (e.g. images) that is not owned by one party. In order to collect all the data, crowdsourcing mechanisms have been widely used to seek help from the crowd. However, existing mechanisms rely on third-party platforms, and the workers from these platforms are not necessarily helpful and redundant data are also not properly handled. To combat this problem, we propose a novel crowdsourcing mechanism based on social networks, where the rewards of the workers are calculated by information entropy and a modified Shapley value. This mechanism incentivizes the workers from the network to not only provide all data they have, but also further invite their neighbours to offer more data. Eventually, the mechanism is able to acquire all data from all workers on the network with a constrained reward spending.

Click to Read Paper and Get Code
Independent Component Analysis (ICA) is an effective unsupervised tool to learn statistically independent representation. However, ICA is not only sensitive to whitening but also difficult to learn an over-complete basis. Consequently, ICA with soft Reconstruction cost(RICA) was presented to learn sparse representations with over-complete basis even on unwhitened data. Whereas RICA is infeasible to represent the data with nonlinear structure due to its intrinsic linearity. In addition, RICA is essentially an unsupervised method and can not utilize the class information. In this paper, we propose a kernel ICA model with reconstruction constraint (kRICA) to capture the nonlinear features. To bring in the class information, we further extend the unsupervised kRICA to a supervised one by introducing a discrimination constraint, namely d-kRICA. This constraint leads to learn a structured basis consisted of basis vectors from different basis subsets corresponding to different class labels. Then each subset will sparsely represent well for its own class but not for the others. Furthermore, data samples belonging to the same class will have similar representations, and thereby the learned sparse representations can take more discriminative power. Experimental results validate the effectiveness of kRICA and d-kRICA for image classification.

* 10 pages, 5 figures
Click to Read Paper and Get Code
In this paper, we propose a deep multiple description coding framework, whose quantizers are adaptively learned via the minimization of multiple description compressive loss. Firstly, our framework is built upon auto-encoder networks, which have multiple description multi-scale dilated encoder network and multiple description decoder networks. Secondly, two entropy estimation networks are learned to estimate the informative amounts of the quantized tensors, which can further supervise the learning of multiple description encoder network to represent the input image delicately. Thirdly, a pair of scalar quantizers accompanied by two importance-indicator maps is automatically learned in an end-to-end self-supervised way. Finally, multiple description structural dis-similarity distance loss is imposed on multiple description decoded images in pixel domain for diversified multiple description generations rather than on feature tensors in feature domain, in addition to multiple description reconstruction loss. Through testing on two commonly used datasets, it is verified that our method is beyond several state-of-the-art multiple description coding approaches in terms of coding efficiency.

* 8 pages, 4 figures
Click to Read Paper and Get Code
In this paper, we propose an image re-sampling compression method by learning virtual codec network (VCN) to resolve the non-differentiable problem of quantization function for image compression. Here, the image re-sampling not only refers to image full-resolution re-sampling but also low-resolution re-sampling. We generalize this method for standard-compliant image compression (SCIC) framework and deep neural networks based compression (DNNC) framework. Specifically, an input image is measured by re-sampling network (RSN) network to get re-sampled vectors. Then, these vectors are directly quantized in the feature space in SCIC, or discrete cosine transform coefficients of these vectors are quantized to further improve coding efficiency in DNNC. At the encoder, the quantized vectors or coefficients are losslessly compressed by arithmetic coding. At the receiver, the decoded vectors are utilized to restore input image by image decoder network (IDN). In order to train RSN network and IDN network together in an end-to-end fashion, our VCN network intimates projection from the re-sampled vectors to the IDN-decoded image. As a result, gradients from IDN network to RSN network can be approximated by VCN network's gradient. Because dimension reduction can be further achieved by quantization in some dimensional space after image re-sampling within auto-encoder architecture, we can well initialize our networks from pre-trained auto-encoder networks. Through extensive experiments and analysis, it is verified that the proposed method has more effectiveness and versatility than many state-of-the-art approaches.

* 13 pages, 11 figures Our project can be found in the website: https://github.com/VirtualCodecNetwork
Click to Read Paper and Get Code
Multiple description coding (MDC) is able to stably transmit the signal in the un-reliable and non-prioritized networks, which has been broadly studied for several decades. However, the traditional MDC doesn't well leverage image's context features to generate multiple descriptions. In this paper, we propose a novel standard-compliant convolutional neural network-based MDC framework in term of image's context features. Firstly, multiple description generator network (MDGN) is designed to produce appearance-similar yet feature-different multiple descriptions automatically according to image's content, which are compressed by standard codec. Secondly, we present multiple description reconstruction network (MDRN) including side reconstruction network (SRN) and central reconstruction network (CRN). When any one of two lossy descriptions is received at the decoder, SRN network is used to improve the quality of this decoded lossy description by removing the compression artifact and up-sampling simultaneously. Meanwhile, we utilize CRN network with two decoded descriptions as inputs for better reconstruction, if both of lossy descriptions are available. Thirdly, multiple description virtual codec network (MDVCN) is proposed to bridge the gap between MDGN network and MDRN network in order to train an end-to-end MDC framework. Here, two learning algorithms are provided to train our whole framework. In addition to structural similarity loss function, the produced descriptions are used as opposing labels with multiple description distance loss function to regularize the training of MDGN network. These losses guarantee that the generated description images are structurally similar yet finely diverse. Experimental results show a great deal of objective and subjective quality measurements to validate the efficiency of the proposed method.

* 13 pages, 3 tables, and 6 figures
Click to Read Paper and Get Code
Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's back-propagation. In this paper, we propose an end-to-end image compression framework based on convolutional neural network to resolve the problem of non-differentiability of the quantization function in the standard codec. First, the feature description neural network is used to get a valid description in the low-dimension space with respect to the ground-truth image so that the amount of image data is greatly reduced for storage or transmission. After image's valid description, standard image codec such as JPEG is leveraged to further compress image, which leads to image's great distortion and compression artifacts, especially blocking artifacts, detail missing, blurring, and ringing artifacts. Then, we use a post-processing neural network to remove these artifacts. Due to the challenge of directly learning a non-linear function for a standard codec based on convolutional neural network, we propose to learn a virtual codec neural network to approximate the projection from the valid description image to the post-processed compressed image, so that the gradient could be efficiently back-propagated from the post-processing neural network to the feature description neural network during training. Meanwhile, an advanced learning algorithm is proposed to train our deep neural networks for compression. Obviously, the priority of the proposed method is compatible with standard existing codecs and our learning strategy can be easily extended into these codecs based on convolutional neural network. Experimental results have demonstrated the advances of the proposed method as compared to several state-of-the-art approaches, especially at very low bit-rate.

* 11 pages, 7 figures
Click to Read Paper and Get Code
Source camera identification is still a hard task in forensics community, especially for the case of the small query image size. In this paper, we propose a solution to identify the source camera of the small-size images: content-adaptive fusion network. In order to learn better feature representation from the input data, content-adaptive convolutional neural networks(CA-CNN) are constructed. We add a convolutional layer in preprocessing stage. Moreover, with the purpose of capturing more comprehensive information, we parallel three CA-CNNs: CA3-CNN, CA5-CNN, CA7-CNN to get the content-adaptive fusion network. The difference of three CA-CNNs lies in the convolutional kernel size of pre-processing layer. The experimental results show that the proposed method is practicable and satisfactory.

* This article has been submitted to the 2017 IEEE International Conference on Image Processing
Click to Read Paper and Get Code
We provide a general framework for characterizing the trade-off between accuracy and robustness in supervised learning. We propose a method and define quantities to characterize the trade-off between accuracy and robustness for a given architecture, and provide theoretical insight into the trade-off. Specifically we introduce a simple trade-off curve, define and study an influence function that captures the sensitivity, under adversarial attack, of the optima of a given loss function. We further show how adversarial training regularizes the parameters in an over-parameterized linear model, recovering the LASSO and ridge regression as special cases, which also allows us to theoretically analyze the behavior of the trade-off curve. In experiments, we demonstrate the corresponding trade-off curves of neural networks and how they vary with respect to factors such as number of layers, neurons, and across different network structures. Such information provides a useful guideline to architecture selection.

Click to Read Paper and Get Code
Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous way of adding supervision to the last layer of the network only and propagating error information up layer-by-layer. In this paper, we propose Deeply-supervised Knowledge Synergy (DKS), a new method aiming to train CNNs with improved generalization ability for image classification tasks without introducing extra computational cost during inference. Inspired by the deeply-supervised learning scheme, we first append auxiliary supervision branches on top of certain intermediate network layers. While properly using auxiliary supervision can improve model accuracy to some degree, we go one step further to explore the possibility of utilizing the probabilistic knowledge dynamically learnt by the classifiers connected to the backbone network as a new regularization to improve the training. A novel synergy loss, which considers pairwise knowledge matching among all supervision branches, is presented. Intriguingly, it enables dense pairwise knowledge matching operations in both top-down and bottom-up directions at each training iteration, resembling a dynamic synergy process for the same task. We evaluate DKS on image classification datasets using state-of-the-art CNN architectures, and show that the models trained with it are consistently better than the corresponding counterparts. For instance, on the ImageNet classification benchmark, our ResNet-152 model outperforms the baseline model with a 1.47% margin in Top-1 accuracy. Code is available at https://github.com/sundw2014/DKS.

* Added supplementary materials, and the code is available at https://github.com/sundw2014/DKS
Click to Read Paper and Get Code
The convolutional neural network (CNN) features can give a good description of image content, which usually represent images with unique global vectors. Although they are compact compared to local descriptors, they still cannot efficiently deal with large-scale image retrieval due to the cost of the linear incremental computation and storage. To address this issue, we build a simple but effective indexing framework based on inverted table, which significantly decreases both the search time and memory usage. In addition, several strategies are fully investigated under an indexing framework to adapt it to CNN features and compensate for quantization errors. First, we use multiple assignment for the query and database images to increase the probability of relevant images' co-existing in the same Voronoi cells obtained via the clustering algorithm. Then, we introduce embedding codes to further improve precision by removing false matches during a search. We demonstrate that by using hashing schemes to calculate the embedding codes and by changing the ranking rule, indexing framework speeds can be greatly improved. Extensive experiments conducted on several unsupervised and supervised benchmarks support these results and the superiority of the proposed indexing framework. We also provide a fair comparison between the popular CNN features.

* 21 pages, 9 figures, submitted to Multimedia Tools and Applications
Click to Read Paper and Get Code
Zero-shot learning (ZSL) aims to recognize objects from novel unseen classes without any training data. Recently, structure-transfer based methods are proposed to implement ZSL by transferring structural knowledge from the semantic embedding space to image feature space to classify testing images. However, we observe that such a knowledge transfer framework may suffer from the problem of the geometric inconsistency between the data in the training and testing spaces. We call this problem as the space shift problem. In this paper, we propose a novel graph based method to alleviate this space shift problem. Specifically, a Shared Reconstruction Graph (SRG) is pursued to capture the common structure of data in the two spaces. With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes. The SRG bridges the image feature space and semantic embedding space. By applying spectral clustering on the learned SRG, many meaningful clusters can be discovered, which interprets ZSL performance on the datasets. Our method can be easily extended to the generalized zero-shot learning setting. Experiments on three popular datasets show that our method outperforms other methods on all datasets. Even with a small number of training samples, our method can achieve the state-of-the-art performance.

Click to Read Paper and Get Code
Convolutional neural networks (CNNs) with deep architectures have substantially advanced the state-of-the-art in computer vision tasks. However, deep networks are typically resource-intensive and thus difficult to be deployed on mobile devices. Recently, CNNs with binary weights have shown compelling efficiency to the community, whereas the accuracy of such models is usually unsatisfactory in practice. In this paper, we introduce network sketching as a novel technique of pursuing binary-weight CNNs, targeting at more faithful inference and better trade-off for practical applications. Our basic idea is to exploit binary structure directly in pre-trained filter banks and produce binary-weight models via tensor expansion. The whole process can be treated as a coarse-to-fine model approximation, akin to the pencil drawing steps of outlining and shading. To further speedup the generated models, namely the sketches, we also propose an associative implementation of binary tensor convolutions. Experimental results demonstrate that a proper sketch of AlexNet (or ResNet) outperforms the existing binary-weight models by large margins on the ImageNet large scale classification task, while the committed memory for network parameters only exceeds a little.

* To appear in CVPR2017
Click to Read Paper and Get Code
Recent studies have demonstrated that the convolutional networks heavily rely on the quality and quantity of generated features. However, in lightweight networks, there are limited available feature information because these networks tend to be shallower and thinner due to the efficiency consideration. For farther improving the performance and accuracy of lightweight networks, we develop Super Interaction Neural Networks (SINet) model from a novel point of view: enhancing the information interaction in neural networks. In order to achieve information interaction along the width of the deep network, we propose Exchange Shortcut Connection, which can integrate the information from different convolution groups without any extra computation cost. And then, in order to achieve information interaction along the depth of the network, we proposed Dense Funnel Layer and Attention based Hierarchical Joint Decision, which are able to make full use of middle layer features. Our experiments show that the superior performance of SINet over other state-of-the-art lightweight models in ImageNet dataset. Furthermore, we also exhibit the effectiveness and universality of our proposed components by ablation studies.

Click to Read Paper and Get Code
Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific inputs. In practice, however, these attacks are difficult to perform and highly constrained by sharing of models through transfer learning. Adversaries have a small window during which they must compromise the student model before it is deployed. In this paper, we describe a significantly more powerful variant of the backdoor attack, latent backdoors, where hidden rules can be embedded in a single "Teacher" model, and automatically inherited by all "Student" models through the transfer learning process. We show that latent backdoors can be quite effective in a variety of application contexts, and validate its practicality through real-world attacks against traffic sign recognition, iris identification of lab volunteers, and facial recognition of public figures (politicians). Finally, we evaluate 4 potential defenses, and find that only one is effective in disrupting latent backdoors, but might incur a cost in classification accuracy as tradeoff.

Click to Read Paper and Get Code
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, with more spectral bands for HSI, while the running time of these methods significantly increases, their denoising performance benefits little. In this paper, we claim that the HSI underlines a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should underlie this global low-rank subspace. This motivates us to propose a unified spatial-spectral paradigm for HSI denoising. As the new model is hard to optimize, we further propose an efficient algorithm for optimization, which is motivated by alternating minimization. This is done by first learning a low-dimensional projection and the related reduced image from the noisy HSI. Then, the non-local low-rank denoising and iterative regularization are developed to refine the reduced image and projection, respectively. Finally, experiments on synthetic and both real datasets demonstrate the superiority against the other state-of-the-arts HSI denoising methods.

Click to Read Paper and Get Code
In this paper, we propose an end-to-end mixed-resolution image compression framework with convolutional neural networks. Firstly, given one input image, feature description neural network (FDNN) is used to generate a new representation of this image, so that this image representation can be more efficiently compressed by standard codec, as compared to the input image. Furthermore, we use post-processing neural network (PPNN) to remove the coding artifacts caused by quantization of codec. Secondly, low-resolution image representation is adopted for high efficiency compression in terms of most of bit spent by image's structures under low bit-rate. However, more bits should be assigned to image details in the high-resolution, when most of structures have been kept after compression at the high bit-rate. This comes from a fact that the low-resolution image representation can't burden more information than high-resolution representation beyond a certain bit-rate. Finally, to resolve the problem of error back-propagation from the PPNN network to the FDNN network, we introduce to learn a virtual codec neural network to imitate two continuous procedures of standard compression and post-processing. The objective experimental results have demonstrated the proposed method has a large margin improvement, when comparing with several state-of-the-art approaches.

* 5 pages, and 2 figures. arXiv admin note: substantial text overlap with arXiv:1712.05969
Click to Read Paper and Get Code
Recently, image forensics community has paied attention to the research on the design of effective algorithms based on deep learning technology and facts proved that combining the domain knowledge of image forensics and deep learning would achieve more robust and better performance than the traditional schemes. Instead of improving it, in this paper, the safety of deep learning based methods in the field of image forensics is taken into account. To the best of our knowledge, this is a first work focusing on this topic. Specifically, we experimentally find that the method using deep learning would fail when adding the slight noise into the images (adversarial images). Furthermore, two kinds of strategys are proposed to enforce security of deep learning-based method. Firstly, an extra penalty term to the loss function is added, which is referred to the 2-norm of the gradient of the loss with respect to the input images, and then an novel training method are adopt to train the model by fusing the normal and adversarial images. Experimental results show that the proposed algorithm can achieve good performance even in the case of adversarial images and provide a safety consideration for deep learning-based image forensics

Click to Read Paper and Get Code
It is known that Boosting can be interpreted as a gradient descent technique to minimize an underlying loss function. Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers. Therefore, several Boosting algorithms, e.g., LogitBoost and SavageBoost, have been proposed to improve the robustness of AdaBoost by replacing the exponential loss with some designed robust loss functions. In this work, we present a new way to robustify AdaBoost, i.e., incorporating the robust learning idea of Self-paced Learning (SPL) into Boosting framework. Specifically, we design a new robust Boosting algorithm based on SPL regime, i.e., SPLBoost, which can be easily implemented by slightly modifying off-the-shelf Boosting packages. Extensive experiments and a theoretical characterization are also carried out to illustrate the merits of the proposed SPLBoost.

* 13 pages, 5 figures
Click to Read Paper and Get Code
Identifying user's identity is a key problem in many data mining applications, such as product recommendation, customized content delivery and criminal identification. Given a set of accounts from the same or different social network platforms, user identification attempts to identify all accounts belonging to the same person. A commonly used solution is to build the relationship among different accounts by exploring their collective patterns, e.g., user profile, writing style, similar comments. However, this kind of method doesn't work well in many practical scenarios, since the information posted explicitly by users may be false due to various reasons. In this paper, we re-inspect the user identification problem from a novel perspective, i.e., identifying user's identity by matching his/her cameras. The underlying assumption is that multiple accounts belonging to the same person contain the same or similar camera fingerprint information. The proposed framework, called User Camera Identification (UCI), is based on camera fingerprints, which takes fully into account the problems of multiple cameras and reposting behaviors.

* 12 pages, 7 figures
Click to Read Paper and Get Code
Object segmentation and object tracking are fundamental research area in the computer vision community. These two topics are diffcult to handle some common challenges, such as occlusion, deformation, motion blur, and scale variation. The former contains heterogeneous object, interacting object, edge ambiguity, and shape complexity. And the latter suffers from difficulties in handling fast motion, out-of-view, and real-time processing. Combining the two problems of video object segmentation and tracking (VOST) can overcome their respective difficulties and improve their performance. VOST can be widely applied to many practical applications such as video summarization, high definition video compression, human computer interaction, and autonomous vehicles. This article aims to provide a comprehensive review of the state-of-the-art tracking methods, and classify these methods into different categories, and identify new trends. First, we provide a hierarchical categorization existing approaches, including unsupervised VOS, semi-supervised VOS, interactive VOS, weakly supervised VOS, and segmentation-based tracking methods. Second, we provide a detailed discussion and overview of the technical characteristics of the different methods. Third, we summarize the characteristics of the related video dataset, and provide a variety of evaluation metrics. Finally, we point out a set of interesting future works and draw our own conclusions.

Click to Read Paper and Get Code