CVPR 2016 论文列表

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.

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.

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.

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.

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.

We propose a novel end-to-end trainable deep network architecture for image denoising based on a Gaussian Conditional Random Field (GCRF) model. In contrast to the existing discriminative denoising methods that train a separate model for each individual noise level, the proposed deep network explicitly models the input noise variance and hence is capable of handling a range of noise levels. Our deep network, which we refer to as deep GCRF network, consists of two sub-networks: (i) a parameter generation network that generates the pairwise potential parameters based on the noisy input image, and ii) an inference network whose layers perform the computations involved in an iterative GCRF inference procedure. We train two deep GCRF networks (each network operates over a range of noise levels: one for low input noise levels and one for high input noise levels) discriminatively by maximizing the peak signal-to-noise ratio measure. Experiments on Berkeley segmentation and PASCALVOC datasets show that the proposed approach produces results on par with the state-of-the-art without training a separate network for each individual noise level.

In this paper, we present a novel Deep Decision Network (DDN) that provides an alternative approach towards building an efficient deep learning network. During the learning phase, starting from the root network node, DDN automatically builds a network that splits the data into disjoint clusters of classes which would be handled by the subsequent expert networks. This results in a tree-like structured network driven by the data. The proposed method provides an insight into the data by identifying the group of classes that are hard to classify and require more attention when compared to others. DDN also has the ability to make early decisions thus making it suitable for time-sensitive applications. We validate DDN on two publicly available benchmark datasets: CIFAR-10 and CIFAR-100 and it yields state-of-the-art classification performance on both the datasets. The proposed algorithm has no limitations to be applied to any generic classification problems.

Salient object detection has recently witnessed substantial progress due to powerful features extracted using deep convolutional neural networks (CNNs). However, existing CNN-based methods operate at the patch level instead of the pixel level. Resulting saliency maps are typically blurry, especially near the boundary of salient objects. Furthermore, image patches are treated as independent samples even when they are overlapping, giving rise to significant redundancy in computation and storage. In this paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations. Our deep network consists of two complementary components, a pixel-level fully convolutional stream and a segment-wise spatial pooling stream. The first stream directly produces a saliency map with pixel-level accuracy from an input image. The second stream extracts segment-wise features very efficiently, and better models saliency discontinuities along object boundaries. Finally, a fully connected CRF model can be optionally incorporated to improve spatial coherence and contour localization in the fused result from these two streams. Experimental results demonstrate that our deep model significantly improves the state of the art.

Machine learning algorithms for the analysis of time-series often depend on the assumption that the utilised data are temporally aligned. Any temporal discrepancies arising in the data is certain to lead to ill-generalisable models, which in turn fail to correctly capture the properties of the task at hand. The temporal alignment of time-series is thus a crucial challenge manifesting in a multitude of applications. Nevertheless, the vast majority of algorithms oriented towards the temporal alignment of time-series are applied directly on the observation space, or utilise simple linear projections. Thus, they fail to capture complex, hierarchical non-linear representations which may prove to be beneficial towards the task of temporal alignment, particularly when dealing with multi-modal data (e.g., aligning visual and acoustic information). To this end, we present the Deep Canonical Time Warping (DCTW), a method which automatically learns complex non-linear representations of multiple time-series, generated such that (i) they are highly correlated, and (ii) temporally in alignment. By means of experiments on four real datasets, we show that the representations learnt via the proposed DCTW significantly outperform state-of-the-art methods in temporal alignment, elegantly handling scenarios with highly heterogeneous features, such as the temporal alignment of acoustic and visual features.

We consider the problem of estimating the spatial layout of an indoor scene from a monocular RGB image, modeled as the projection of a 3D cuboid. Existing solutions to this problem often rely strongly on hand-engineered features and vanishing point detection, which are prone to failure in the presence of clutter. In this paper, we present a method that uses a fully convolutional neural network (FCNN) in conjunction with a novel optimization framework for generating layout estimates. We demonstrate that our method is robust in the presence of clutter and handles a wide range of highly challenging scenes. We evaluate our method on two standard benchmarks and show that it achieves state of the art results, outperforming previous methods by a wide margin.

Traditional1 salient object detection models often use hand-crafted features to formulate contrast and various prior knowledge, and then combine them artificially. In this work, we propose a novel end-to-end deep hierarchical saliency network (DHSNet) based on convolutional neural networks for detecting salient objects. DHSNet first makes a coarse global prediction by automatically learning various global structured saliency cues, including global contrast, objectness, compactness, and their optimal combination. Then a novel hierarchical recurrent convolutional neural network (HRCNN) is adopted to further hierarchically and progressively refine the details of saliency maps step by step via integrating local context information. The whole architecture works in a global to local and coarse to fine manner. DHSNet is directly trained using whole images and corresponding ground truth saliency masks. When testing, saliency maps can be generated by directly and efficiently feedforwarding testing images through the network, without relying on any other techniques. Evaluations on four benchmark datasets and comparisons with other 11 state-of-the-art algorithms demonstrate that DHSNet not only shows its significant superiority in terms of performance, but also achieves a real-time speed of 23 FPS on modern GPUs.

The morphology of glands has been used routinely by pathologists to assess the malignancy degree of adenocarcinomas. Accurate segmentation of glands from histology images is a crucial step to obtain reliable morphological statistics for quantitative diagnosis. In this paper, we proposed an efficient deep contour-aware network (DCAN) to solve this challenging problem under a unified multi-task learning framework. In the proposed network, multi-level contextual features from the hierarchical architecture are explored with auxiliary supervision for accurate gland segmentation. When incorporated with multi-task regularization during the training, the discriminative capability of intermediate features can be further improved. Moreover, our network can not only output accurate probability maps of glands, but also depict clear contours simultaneously for separating clustered objects, which further boosts the gland segmentation performance. This unified framework can be efficient when applied to large-scale histopathological data without resorting to additional steps to generate contours based on low-level cues for post-separating. Our method won the 2015 MICCAI Gland Segmentation Challenge out of 13 competitive teams, surpassing all the other methods by a significant margin.

In image labeling, local representations for image units (pixels, patches or superpixels) are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded. In this paper, we introduce recurrent neural networks (RNNs) to address this issue. Specifically, directed acyclic graph RNNs (DAG-RNNs) are proposed to process DAG-structured images, which enables the network to model long-range semantic dependencies among image units. Our DAG-RNNs are capable of tremendously enhancing the discriminative power of local representations, which significantly benefits the local classification. Meanwhile, we propose a novel class weighting function that attends to rare classes, which phenomenally boosts the recognition accuracy for non-frequent classes. Integrating with convolution and deconvolution layers, our DAG-RNNs achieve new state-of-the-art results on the challenging SiftFlow, CamVid and Barcelona benchmarks.