ICCV 2017 论文列表

Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning. Learning such mappings from unlabelled data, or improving upon supervised models by exploiting unlabelled data, remains elusive. We argue that there are two important parts to learning without annotations: (i) matching the predictions to the input observations, and (ii) matching the predictions to known priors. We propose Adversarial Inverse Graphics networks (AIGNs): weakly supervised neural network models that combine feedback from rendering their predictions, with distribution matching between their predictions and a collection of ground-truth factors. We apply AIGNs to 3D human pose estimation and 3D structure and egomotion estimation, and outperform models supervised by only paired annotations. We further apply AIGNs to facial image transformation using super-resolution and inpainting renderers, while deliberately adding biases in the ground-truth datasets. Our model seamlessly incorporates such biases, rendering input faces towards young, old, feminine, masculine or Tom Cruise-like equivalents (depending on the chosen bias), or adding lip and nose augmentations while inpainting concealed lips and noses.

Users like sharing personal photos with others through social media. At the same time, they might want to make automatic identification in such photos difficult or even impossible. Classic obfuscation methods such as blurring are not only unpleasant but also not as effective as one would expect. Recent studies on adversarial image perturbations (AIP) suggest that it is possible to confuse recognition systems effectively without unpleasant artifacts. However, in the presence of counter measures against AIPs, it is unclear how effective AIP would be in particular when the choice of counter measure is unknown. Game theory provides tools for studying the interaction between agents with uncertainties in the strategies. We introduce a general game theoretical framework for the user-recogniser dynamics, and present a case study that involves current state of the art AIP and person recognition techniques. We derive the optimal strategy for the user that assures an upper bound on the recognition rate independent of the recogniser's counter measure. Code is available at https://goo.gl/hgvbNK.

It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, cause deep networks to fail on image classification. In this paper, we extend adversarial examples to semantic segmentation and object detection which are much more difficult. Our observation is that both segmentation and detection are based on classifying multiple targets on an image (e.g., the target is a pixel or a receptive field in segmentation, and an object proposal in detection). This inspires us to optimize a loss function over a set of targets for generating adversarial perturbations. Based on this, we propose a novel algorithm named Dense Adversary Generation (DAG), which applies to the state-of-the-art networks for segmentation and detection. We find that the adversarial perturbations can be transferred across networks with different training data, based on different architectures, and even for different recognition tasks. In particular, the transfer ability across networks with the same architecture is more significant than in other cases. Besides, we show that summing up heterogeneous perturbations often leads to better transfer performance, which provides an effective method of black-box adversarial attack.

Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on detecting those adversarial examples by analyzing whether they come from the same distribution as the normal examples. Instead of directly training a deep neural network to detect adversarials, a much simpler approach was proposed based on statistics on outputs from convolutional layers. A cascade classifier was designed to efficiently detect adversarials. Furthermore, trained from one particular adversarial generating mechanism, the resulting classifier can successfully detect adversarials from a completely different mechanism as well. The resulting classifier is non-subdifferentiable, hence creates a difficulty for adversaries to attack by using the gradient of the classifier. After detecting adversarial examples, we show that many of them can be recovered by simply performing a small average filter on the image. Those findings should lead to more insights about the classification mechanisms in deep convolutional neural networks.

In this work, we present the RNN Tree (RNN-T), an adaptive learning framework for skeleton based human action recognition. Our method categorizes action classes and uses multiple Recurrent Neural Networks (RNNs) in a tree-like hierarchy. The RNNs in RNN-T are co-trained with the action category hierarchy, which determines the structure of RNN-T. Actions in skeletal representations are recognized via a hierarchical inference process, during which individual RNNs differentiate finer-grained action classes with increasing confidence. Inference in RNN-T ends when any RNN in the tree recognizes the action with high confidence, or a leaf node is reached. RNN-T effectively addresses two main challenges of large-scale action recognition: (i) able to distinguish fine-grained action classes that are intractable using a single network, and (ii) adaptive to new action classes by augmenting an existing model. We demonstrate the effectiveness of RNN-T/ACH method and compare it with the state-of-the-art methods on a large-scale dataset and several existing benchmarks.

Object detection aims at high speed and accuracy simultaneously. However, fast models are usually less accurate, while accurate models cannot satisfy our need for speed. A fast model can be 10 times faster but 50% less accurate than an accurate model. In this paper, we propose Adaptive Feeding (AF) to combine a fast (but less accurate) detector and an accurate (but slow) detector, by adaptively determining whether an image is easy or hard and choosing an appropriate detector for it. In practice, we build a cascade of detectors, including the AF classifier which make the easy vs. hard decision and the two detectors. The AF classifier can be tuned to obtain different tradeoff between speed and accuracy, which has negligible training time and requires no additional training data. Experimental results on the PASCAL VOC, MS COCO and Caltech Pedestrian datasets confirm that AF has the ability to achieve comparable speed as the fast detector and comparable accuracy as the accurate one at the same time. As an example, by combining the fast SSD300 with the accurate SSD500 detector, AF leads to 50% speedup over SSD500 with the same precision on the VOC2007 test set.

Annotating human poses in realistic scenes is very time consuming, yet necessary for training human pose estimators. We propose to address this problem in an active learning framework, which alternates between requesting the most useful annotations among a large set of unlabelled images, and re-training the pose estimator. To this end, (1) we propose an uncertainty estimator specific for body joint predictions, which takes into account the spatial distribution of the responses of the current pose estimator on the unlabelled images; (2) we propose a dynamic combination of influence and uncertainty cues, where their weights vary during the active learning process according to the reliability of the current pose estimator; (3) we introduce a computer assisted annotation interface, which reduces the time necessary for a human annotator to click on a joint by discretizing the image into regions generated by the current pose estimator. Experiments using the MPII and LSP datasets with both simulated and real annotators show that (1) the proposed active selection scheme outperforms several baselines; (2) our computer-assisted interface can further reduce annotation effort; and (3) our technique can further improve the performance of a pose estimator even when starting from an already strong one.performance in 23% annotation time.

This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a profoundly different approach: we ask for annotations of the decision boundary. We achieve this using a deep generative model to create novel instances along a 1d vector. A point on the decision boundary is revealed where the instances change class. Experimentally we show on three datasets that our method can be plugged-in to other active learning schemes, that human oracles can effectively annotate point on the decision boundary, and that decision boundary annotations improve over single sample instance annotations.

Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, ie, sequences of bounding boxes with associated scores. The same way state-of-the-art object detectors rely on anchor boxes, our ACT-detector is based on anchor cuboids. We build upon the SSD framework. Convolutional features are extracted for each frame, while scores and regressions are based on the temporal stacking of these features, thus exploiting information from a sequence. Our experimental results show that leveraging sequences of frames significantly improves detection performance over using individual frames. The gain of our tubelet detector can be explained by both more accurate scores and more precise localization. Our ACT-detector outperforms the state-of-the-art methods for frame-mAP and video-mAP on the J-HMDB and UCF-101 datasets, in particular at high overlap thresholds.

This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN, we witness a large improvement of the object detection performance on hazy images.

Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically depart from current practice, and take a first step towards the design and implementation of a deep network architecture able to classify and regress whole video subsets, so providing a truly optimal solution of the action detection problem. In this work, in particular, we propose a novel deep net framework able to regress and classify 3D region proposals spanning two successive video frames, whose core is an evolution of classical region proposal networks (RPNs). As such, our 3D-RPN net is able to effectively encode the temporal aspect of actions by purely exploiting appearance, as opposed to methods which heavily rely on expensive flow maps. The proposed model is end-to-end trainable and can be jointly optimised for action localisation and classification in a single step. At test time the network predicts "micro-tubes" encompassing two successive frames, which are linked up into complete action tubes via a new algorithm which exploits the temporal encoding learned by the network and cuts computation time by 50%. Promising results on the J-HMDB-21 and UCF-101 action detection datasets show that our model does outperform the state-of-the-art when relying purely on appearance.

We introduce Appearance-MAT (AMAT), a generalization of the medial axis transform for natural images, that is framed as a weighted geometric set cover problem. We make the following contributions: i) we extend previous medial point detection methods for color images, by associating each medial point with a local scale; ii) inspired by the invertibility property of the binary MAT, we also associate each medial point with a local encoding that allows us to invert the AMAT, reconstructing the input image; iii) we describe a clustering scheme that takes advantage of the additional scale and appearance information to group individual points into medial branches, providing a shape decomposition of the underlying image regions. In our experiments, we show state-of-the-art performance in medial point detection on Berkeley Medial AXes (BMAX500), a new dataset of medial axes based on the BSDS500 database, and good generalization on the SK506 and WH-SYMMAX datasets. We also measure the quality of reconstructed images from BMAX500, obtained by inverting their computed AMAT. Our approach delivers significantly better reconstruction quality wrt to three baselines, using just 10% of the image pixels. Our code and annotations are available at https://github.com/tsogkas/amat .

We propose a novel convolutional neural network architecture for estimating geospatial functions such as population density, land cover, or land use. In our approach, we combine overhead and ground-level images in an end-to-end trainable neural network, which uses kernel regression and density estimation to convert features extracted from the ground-level images into a dense feature map. The output of this network is a dense estimate of the geospatial function in the form of a pixel-level labeling of the overhead image. To evaluate our approach, we created a large dataset of overhead and ground-level images from a major urban area with three sets of labels: land use, building function, and building age. We find that our approach is more accurate for all tasks, in some cases dramatically so.

Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem. State-of-the-art deep learning methods can now estimate accurate 2D depth maps, but when the maps are projected into 3D, they lack local detail and are often highly distorted. We propose a fast-to-train two-streamed CNN that predicts depth and depth gradients, which are then fused together into an accurate and detailed depth map. We also define a novel set loss over multiple images; by regularizing the estimation between a common set of images, the network is less prone to over-fitting and achieves better accuracy than competing methods. Experiments on the NYU Depth v2 dataset shows that our depth predictions are competitive with state-of-the-art and lead to faithful 3D projections.

Person re-identification is an important task in video surveillance systems. It can be formally defined as establishing the correspondence between images of a person taken from different cameras at different times. In this pa- per, we present a two stream convolutional neural network where each stream is a Siamese network. This architecture can learn spatial and temporal information separately. We also propose a weighted two stream training objective function which combines the Siamese cost of the spatial and temporal streams with the objective of predicting a person's identity. We evaluate our proposed method on the publicly available PRID2011 and iLIDS-VID datasets and demonstrate the efficacy of our proposed method. On average, the top rank matching accuracy is 4% higher than the accuracy achieved by the cross-view quadratic discriminant analysis used in combination with the hierarchical Gaussian descriptor (GOG+XQDA), and 5% higher than the recurrent neural network method.

Deep convolutional neural networks (CNNs) have been successfully applied to a wide variety of problems in computer vision, including salient object detection. To detect and segment salient objects accurately, it is necessary to extract and combine high-level semantic features with low-level fine details simultaneously. This happens to be a challenge for CNNs as repeated subsampling operations such as pooling and convolution lead to a significant decrease in the initial image resolution, which results in loss of spatial details and finer structures. To remedy this problem, here we propose to augment feedforward neural networks with a novel pyramid pooling module and a multi-stage refinement mechanism for saliency detection. First, our deep feedward net is used to generate a coarse prediction map with much detailed structures lost. Then, refinement nets are integrated with local context information to refine the preceding saliency maps generated in the master branch in a stagewise manner. Further, a pyramid pooling module is applied for different region-based global context aggregation. Empirical evaluations over five benchmark datasets show that our proposed method compares favorably against the state-of-the-art approaches.

This paper presents a novel hierarchical spatiotemporal orientation representation for spacetime image analysis. It is designed to combine the benefits of the multilayer architecture of ConvNets and a more controlled approach to spacetime analysis. A distinguishing aspect of the approach is that unlike most contemporary convolutional networks no learning is involved; rather, all design decisions are specified analytically with theoretical motivations. This approach makes it possible to understand what information is being extracted at each stage and layer of processing as well as to minimize heuristic choices in design. Another key aspect of the network is its recurrent nature, whereby the output of each layer of processing feeds back to the input. To keep the network size manageable across layers, a novel cross-channel feature pooling is proposed. The multilayer architecture that results systematically reveals hierarchical image structure in terms of multiscale, multiorientation properties of visual spacetime. To illustrate its utility, the network has been applied to the task of dynamic texture recognition. Empirical evaluation on multiple standard datasets shows that it sets a new state-of-the-art.

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (i.e., using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

Many spectral clustering algorithms have been proposed and successfully applied to image data analysis such as content based image retrieval, image annotation, and image indexing. Conventional spectral clustering algorithms usually involve a two-stage process: eigendecomposition of similarity matrix and clustering assignments from eigenvectors by k-means or spectral rotation. However, the final clustering assignments obtained by the two-stage process may deviate from the assignments by directly optimize the original objective function. Moreover, most of these methods usually have very high computational complexities. In this paper, we propose a new min-cut algorithm for image clustering, which scales linearly to the data size. In the new method, a self-balanced min-cut model is proposed in which the Exclusive Lasso is implicitly introduced as a balance regularizer in order to produce balanced partition. We propose an iterative algorithm to solve the new model, which has a time complexity of O(n) where n is the number of samples. Theoretical analysis reveals that the new method can simultaneously minimize the graph cut and balance the partition across all clusters. A series of experiments were conducted on both synthetic and benchmark data sets and the experimental results show the superior performance of the new method.