CVPR 2016 论文列表

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions). Increasing recursion depth can improve performance without introducing new parameters for additional convolutions. Albeit advantages, learning a DRCN is very hard with a standard gradient descent method due to exploding/ vanishing gradients. To ease the difficulty of training, we propose two extensions: recursive supervision and skip-connection. Our method outperforms previous methods by a large margin.

Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision [22, 32], but their use in graphics problems has been limited ([23, 7] are notable recent exceptions). In this work, we present a novel deep architecture that per- forms new view synthesis directly from pixels, trained from a large number of posed image sets. In contrast to tradi- tional approaches which consist of multiple complex stages of processing, each of which require careful tuning and can fail in unexpected ways, our system is trained end-to-end. The pixels from neighboring views of a scene are presented to the network which then directly produces the pixels of the unseen view. The benefits of our approach include gen- erality (we only require posed image sets and can easily apply our method to different domains), and high quality results on traditionally difficult scenes. We believe this is due to the end-to-end nature of our system which is able to plausibly generate pixels according to color, depth, and tex- ture priors learnt automatically from the training data. We show view interpolation results on imagery from the KITTI dataset [12], from data from [1] as well as on StreetView images. To our knowledge, our work is the first to apply deep learning to the problem of new view synthesis from sets of real-world, natural imagery.

We propose DeepHand to estimate the 3D pose of a hand using depth data from commercial 3D sensors. We discriminatively train convolutional neural networks to output a low dimensional activation feature given a depth map. This activation feature vector is representative of the global or local joint angle parameters of a hand pose. We efficiently identify 'spatial' nearest neighbors to the activation feature, from a database of features corresponding to synthetic depth maps, and store some 'temporal' neighbors from previous frames. Our matrix completion algorithm uses these 'spatio-temporal' activation features and the corresponding known pose parameter values to to estimate the unknown pose parameters of the input feature vector. Our database of activation features supplements large viewpoint coverage and our hierarchical estimation of pose parameters is robust to occlusions. We show that our approach compares favorably to state-of-the-art methods while achieving real time performance (32 FPS) on a standard computer.

State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. Despite the importance of this phenomenon, no effective methods have been proposed to accurately compute the robustness of state-of-the-art deep classifiers to such perturbations on large-scale datasets. In this paper, we fill this gap and propose the DeepFool algorithm to efficiently compute perturbations that fool deep networks, and thus reliably quantify the robustness of these classifiers. Extensive experimental results show that our approach outperforms recent methods in the task of computing adversarial perturbations and making classifiers more robust.

Recent advances in clothes recognition have been driven by the construction of clothes datasets. Existing datasets are limited in the amount of annotations and are difficult to cope with the various challenges in real-world applications. In this work, we introduce DeepFashion, a large-scale clothes dataset with comprehensive annotations. It contains over 800,000 images, which are richly annotated with massive attributes, clothing landmarks, and correspondence of images taken under different scenarios including store, street snapshot, and consumer. Such rich annotations enable the development of powerful algorithms in clothes recognition and facilitating future researches. To demonstrate the advantages of DeepFashion, we propose a new deep model, namely FashionNet, which learns clothing features by jointly predicting clothing attributes and landmarks. The estimated landmarks are then employed to pool or gate the learned features. It is optimized in an iterative manner. Extensive experiments demonstrate the effectiveness of FashionNet and the usefulness of DeepFashion.

This paper considers the task of articulated human pose estimation of multiple people in real world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other. This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.

The recognition of human actions and the determination of human attributes are two tasks that call for fine-grained classification. Indeed, often rather small and inconspicuous objects and features have to be detected to tell their classes apart. In order to deal with this challenge, we propose a novel convolutional neural network that mines mid-level image patches that are sufficiently dedicated to resolve the corresponding subtleties. In particular, we train a newly designed CNN (DeepPattern) that learns discriminative patch groups. There are two innovative aspects to this. On the one hand we pay attention to contextual information in an original fashion. On the other hand, we let an iteration of feature learning and patch clustering purify the set of dedicated patches that we use. We validate our method for action classification on two challenging datasets: PASCAL VOC 2012 Action and Stanford 40 Actions, and for attribute recognition we use the Berkeley Attributes of People dataset. Our discriminative mid-level mining CNN obtains state-of-the-art results on these datasets, without a need for annotations about parts and poses.

In this paper, we present a new hashing method to learn compact binary codes for highly efficient image retrieval on large-scale datasets. While the complex image appearance variations still pose a great challenge to reliable retrieval, in light of the recent progress of Convolutional Neural Networks (CNNs) in learning robust image representation on various vision tasks, this paper proposes a novel Deep Supervised Hashing (DSH) method to learn compact similarity-preserving binary code for the huge body of image data. Specifically, we devise a CNN architecture that takes pairs of images (similar/dissimilar) as training inputs and encourages the output of each image to approximate discrete values (e.g. +1/-1). To this end, a loss function is elaborately designed to maximize the discriminability of the output space by encoding the supervised information from the input image pairs, and simultaneously imposing regularization on the real-valued outputs to approximate the desired discrete values. For image retrieval, new-coming query images can be easily encoded by propagating through the network and then quantizing the network outputs to binary codes representation. Extensive experiments on two large scale datasets CIFAR-10 and NUS-WIDE show the promising performance of our method compared with the state-of-the-arts.

This paper addresses the problem of structured scene parsing, i.e., parsing the input scene into a configuration including hierarchical semantic objects with their interaction relations. We propose a deep architecture consisting of two networks: i) a convolutional neural network (CNN) extracting the image representation for pixelwise object labeling and ii) a recursive neural network (RNN) discovering the hierarchical object structure and the inter-object relations. Rather than relying on elaborative annotations (e.g., manually labeled semantic maps and relations), we train our deep model in a weakly-supervised manner by leveraging the descriptive sentences of the training images. Specifically, we decompose each sentence into a semantic tree consisting of nouns and verb phrases, and facilitate these trees discovering the configurations of the training images. Once these scene configurations are determined, then the parameters of both the CNN and RNN are updated accordingly by back propagation. The entire model training is accomplished through an Expectation-Maximization method. Extensive experiments suggest that our model is capable of producing meaningful and structured scene configurations and achieving more favorable scene labeling performance on PASCAL VOC 2012 over other state-of-the-art weakly-supervised methods.

We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a 3D volumetric scene from a RGB-D image as input and outputs 3D object bounding boxes. In our approach, we propose the first 3D Region Proposal Network (RPN) to learn objectness from geometric shapes and the first joint Object Recognition Network (ORN) to extract geometric features in 3D and color features in 2D. In particular, we handle objects of various sizes by training an amodal RPN at two different scales and an ORN to regress 3D bounding boxes. Experiments show that our algorithm outperforms the state-of-the-art by 13.8 in mAP and is 200x faster than the original Sliding Shapes.

We present a deep layered architecture that generalizes convolutional neural networks (ConvNets). The architecture, called SimNets, is driven by two operators: (i) a similarity function that generalizes inner-product, and (ii) a log-mean-exp function called MEX that generalizes maximum and average. The two operators applied in succession give rise to a standard neuron but in "feature space". The feature spaces realized by SimNets depend on the choice of the similarity operator. The simplest setting, which corresponds to a convolution, realizes the feature space of the Exponential kernel, while other settings realize feature spaces of more powerful kernels (Generalized Gaussian, which includes as special cases RBF and Laplacian), or even dynamically learned feature spaces (Generalized Multiple Kernel Learning). As a result, the SimNet contains a higher abstraction level compared to a traditional ConvNet. We argue that enhanced expressiveness is important when the networks are small due to run-time constraints (such as those imposed by mobile applications). Empirical evaluation validates the superior expressiveness of SimNets, showing a significant gain in accuracy over ConvNets when computational resources at run-time are limited. We also show that in large-scale settings, where computational complexity is less of a concern, the additional capacity of SimNets can be controlled with proper regularization, yielding accuracies comparable to state of the art ConvNets.

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. They have demonstrated superior results over previous works that utilize hand-crafted low level features for saliency detection. In this paper, we demonstrate that the hand-crafted features can provide complementary effects to enhance performance of saliency detection that utilizes only high level features. Our method utilizes both high level and low level features for saliency detection under a unified deep learning framework. The high level features are extracted using the VGG-net, and the low level features are compared with other parts of an image to form a low level distance map. The low level distance map is then encoded using a CNN with multiple 1*1 convolutional and ReLU layers. We concatenate the encoded low level distance map and the high level features, and connect them to a fully connected neural network classifier to evaluate the saliency of a query region. Our experiments show that our method can further improve performance of the state-of-the-art deep learning based saliency detection methods.

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

The growing explosion in the use of surveillance cameras in public security highlights the importance of vehicle search from a large-scale image or video database. However, compared with person re-identification or face recognition, vehicle search problem has long been neglected by researchers in vision community. This paper focuses on an interesting but challenging problem, vehicle re-identification (a.k.a precise vehicle search). We propose a Deep Relative Distance Learning (DRDL) method which exploits a two-branch deep convolutional network to project raw vehicle images into an Euclidean space where distance can be directly used to measure the similarity of arbitrary two vehicles. To further facilitate the future research on this problem, we also present a carefully-organized large-scale image database "VehicleID", which includes multiple images of the same vehicle captured by different real-world cameras in a city. We evaluate our DRDL method on our VehicleID dataset and another recently-released vehicle model classification dataset "CompCars" in three sets of experiments: vehicle re-identification, vehicle model verification and vehicle retrieval. Experimental results show that our method can achieve promising results and outperforms several state-of-the-art approaches.

Region learning (RL) and multi-label learning (ML) have recently attracted increasing attentions in the field of facial Action Unit (AU) detection. Knowing that AUs are active on sparse facial regions, RL aims to identify these regions for a better specificity. On the other hand, a strong statistical evidence of AU correlations suggests that ML is a natural way to model the detection task. In this paper, we propose Deep Region and Multi-label Learning (DRML), a unified deep network that simultaneously addresses these two problems. One crucial aspect in DRML is a novel region layer that uses feed-forward functions to induce important facial regions, forcing the learned weights to capture structural information of the face. Our region layer serves as an alternative design between locally connected layers (i.e., confined kernels to individual pixels) and conventional convolution layers (i.e., shared kernels across an entire image). Unlike previous studies that solve RL and ML alternately, DRML by construction addresses both problems, allowing the two seemingly irrelevant problems to interact more directly. The complete network is end-to-end trainable, and automatically learns representations robust to variations inherent within a local region. Experiments on BP4D and DISFA benchmarks show that DRML performs the highest average F1-score and AUC within and across datasets in comparison with alternative methods.

Undoing the image formation process and therefore decomposing appearance into its intrinsic properties is a challenging task due to the under-constraint nature of this inverse problem. While significant progress has been made on inferring shape, materials and illumination from images only, progress in unconstrained setting is still limited. We propose a fully convolutional neural architecture to estimate reflectance maps of specular materials in natural lighting conditions. We achieve this in an end-to-end learning formulation that directly predicts a reflectance map from the image itself. We show how to improve estimates by facilitating additional supervision in an indirect scheme that first predicts surface orientation and afterwards predicts the reflectance map by a learning-based sparse data interpolation. In order to analyze performance on this difficult task, we propose a new challenge of Specular MAterials on SHapes with complex IllumiNation (SMASHINg) using both synthetic and real images. Furthermore, we show the application our method to a range of image-based editing tasks on real images.

Learning the distance metric between pairs of examples is of great importance for learning and visual recognition. With the remarkable success from the state of the art convolutional neural networks, recent works have shown promising results on discriminatively training the networks to learn semantic feature embeddings where similar examples are mapped close to each other and dissimilar examples are mapped farther apart. In this paper, we describe an algorithm for taking full advantage of the training batches in the neural network training by lifting the vector of pairwise distances within the batch to the matrix of pairwise distances. This step enables the algorithm to learn the state of the art feature embedding by optimizing a novel structured prediction objective for active hard negative mining on the lifted problem. Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning. Our experiments on the CUB-200-2011, CARS196, and Online Products datasets demonstrate significant improvement over existing deep feature embedding methods on all experimented embedding sizes with the GoogLeNet network. The source code and the dataset are available at: https://github.com/rksltnl/Deep-Metric-Learning-CVPR16

Interactive object selection is a very important research problem and has many applications. Previous algorithms require substantial user interactions to estimate the foreground and background distributions. In this paper, we present a novel deep-learning-based algorithm which has much better understanding of objectness and can reduce user interactions to just a few clicks. Our algorithm transforms user-provided positive and negative clicks into two Euclidean distance maps which are then concatenated with the RBG channels of images to compose (image, user interactions) pairs. We generate many of such pairs by combining several random sampling strategies to model users' click patterns and use them to finetune deep Fully Convolutional Networks (FCNs). Finally the output probability maps of our FCN-8s model is integrated with graph cut optimization to refine the boundary segments. Our model is trained on the PASCAL segmentation dataset and evaluated on other datasets with different object classes. Experimental results on both seen and unseen objects clearly demonstrate that our algorithm has a good generalization ability and is superior to all existing interactive object selection approaches.

This work presents a new approach to learning a frame-based classifier on weakly labelled sequence data by embedding a CNN within an iterative EM algorithm. This allows the CNN to be trained on a vast number of example images when only loose sequence level information is available for the source videos. Although we demonstrate this in the context of hand shape recognition, the approach has wider application to any video recognition task where frame level labelling is not available. The iterative EM algorithm leverages the discriminative ability of the CNN to iteratively refine the frame level annotation and subsequent training of the CNN. By embedding the classifier within an EM framework the CNN can easily be trained on 1 million hand images. We demonstrate that the final classifier generalises over both individuals and data sets. The algorithm is evaluated on over 3000 manually labelled hand shape images of 60 different classes which will be released to the community. Furthermore, we demonstrate its use in continuous sign language recognition on two publicly available large sign language data sets, where it outperforms the current state-of-the-art by a large margin. To our knowledge no previous work has explored expectation maximization without Gaussian mixture models to exploit weak sequence labels for sign language recognition.