Easy availability of wearable egocentric cameras, and the sense of privacy propagated by the fact that the wearer is never seen in the captured videos, has led to a tremendous rise in public sharing of such videos. Unlike hand-held cameras, egocentric cameras are harnessed on the wearer’s head, which makes it possible to track the wearer’s head motion by observing optical flow in the egocentric videos. In this work, we create a novel kind of privacy attack by extracting the wearer’s gait profile, a well known biometric signature, from such optical flow in the egocentric videos. We demonstrate strong wearer recognition capabilities based on extracted gait features, an unprecedented and critical weakness completely absent in hand-held videos. We demonstrate the following attack scenarios: (1) In a closed-set scenario, we show that it is possible to recognize the wearer of an egocentric video with an accuracy of more than 92.5% on the benchmark video dataset. (2) In an open-set setting, when the system has not seen the camera wearer even once during the training, we show that it is still possible to identify that the two egocentric videos have been captured by the same wearer with an Equal Error Rate (EER) of less than 14.35%. (3) We show that it is possible to extract gait signature even if only sparse optical flow and no other scene information from egocentric video is available. We demonstrate the accuracy of more than 84% for wearer recognition with only global optical flow. (4) While the first person to first person matching does not give us access to the wearer’s face, we show that it is possible to match the extracted gait features against the one obtained from a third person view such as a surveillance camera looking at the wearer in a completely different background at a different time. In essence, our work indicates that sharing one’s egocentric video should be treated as giving away one’s biometric identity and recommend much more oversight before sharing of egocentric videos. The code, trained models, and the datasets and their annotations are available at https://egocentricbiometric.github.io/
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
We propose a novel method for neural network quantization that casts the neural architecture search problem as one of hyperparameter search to find non-uniform bit distributions throughout the layers of a CNN. We perform the search assuming a Multi-Task Gaussian Processes prior, which splits the problem to multiple tasks, each corresponding to different number of training epochs, and explore the space by sampling those configurations that yield maximum information. We then show that with significantly lower precision in the last layers we achieve a minimal loss of accuracy with appreciable memory savings. We test our findings on the CIFAR10 and ImageNet datasets using the VGG, ResNet and GoogLeNet architectures.
Single image deraining regards an input image as a fusion of a background image, a transmission map, rain streaks, and atmosphere light. While advanced models are proposed for image restoration (i.e., background image generation), they regard rain streaks with the same properties as background rather than transmission medium. As vapors (i.e., rain streaks accumulation or fog-like rain) are conveyed in the transmission map to model the veiling effect, the fusion of rain streaks and vapors do not naturally reflect the rain image formation. In this work, we reformulate rain streaks as transmission medium together with vapors to model rain imaging. We propose an encoder-decoder CNN named as SNet to learn the transmission map of rain streaks. As rain streaks appear with various shapes and directions, we use ShuffleNet units within SNet to capture their anisotropic representations. As vapors are brought by rain streaks, we propose a VNet containing spatial pyramid pooling (SSP) to predict the transmission map of vapors in multi-scales based on that of rain streaks. Meanwhile, we use an encoder CNN named ANet to estimate atmosphere light. The SNet, VNet, and ANet are jointly trained to predict transmission maps and atmosphere light for rain image restoration. Extensive experiments on the benchmark datasets demonstrate the effectiveness of the proposed visual model to predict rain streaks and vapors. The proposed deraining method performs favorably against state-of-the-art deraining approaches.
Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
PDF ↗In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based methods. The proposed model consists of two sub-models parameterized by neural networks: (1) a saliency predictor that maps input images to clean saliency maps, and (2) a noise generator, which is a latent variable model that produces noises from Gaussian latent vectors. The whole model that represents noisy labels is a sum of the two sub-models. The goal of training the model is to estimate the parameters of both sub-models, and simultaneously infer the corresponding latent vector of each noisy label. We propose to train the model by using an alternating back-propagation (ABP) algorithm, which alternates the following two steps: (1) learning back-propagation for estimating the parameters of two sub-models by gradient ascent, and (2) inferential back-propagation for inferring the latent vectors of training noisy examples by Langevin Dynamics. To prevent the network from converging to trivial solutions, we utilize an edge-aware smoothness loss to regularize hidden saliency maps to have similar structures as their corresponding images. Experimental results on several benchmark datasets indicate the effectiveness of the proposed model.
Image-level label based weakly-supervised semantic segmentation (WSSS) aims to adopt image-level labels to train semantic segmentation models, saving vast human labors for costly pixel-level annotations. A typical pipeline for this problem is first to adopt class activation maps (CAM) with image-level labels to generate pseudo-masks (a.k.a. seeds) and then use them for training segmentation models. The main difficulty is that seeds are usually sparse and incomplete. Related works typically try to alleviate this problem by adopting many bells and whistles to enhance the seeds. Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model's robustness to learn from multiple seeds. We managed to generate many different seeds for each image, which are different estimates of the underlying ground truth. The segmentation model simultaneously exploits these seeds to learn and automatically decides the confidence of each seed. Extensive experiments on Pascal VOC 2012 demonstrate the advantage of this multi-seeds strategy over previous state-of-the-art.
Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients, which can be solved, for example, using a half-quadratic splitting method with Richardson fixed-point iterations for its least-squares updates and a proximal operator for the auxiliary variable updates. We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels. Using convolutions instead of a generic linear preconditioner allows extremely efficient parameter sharing across the image, and leads to significant gains in accuracy and/or speed compared to classical FFT and conjugate-gradient methods. More importantly, the proposed architecture is easily adapted to learning both the preconditioner and the proximal operator using CNN embeddings. This yields a simple and efficient algorithm for non-blind image deblurring which is fully interpretable, can be learned end to end, and whose accuracy matches or exceeds the state of the art, quite significantly, in the non-uniform case.
An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which consists of the annotation network (A-Net) and the transfer network (T-Net). First, given user scribbles on a frame, A-Net yields a segmentation result based on the encoder-decoder architecture. Second, T-Net transfers the segmentation result bidirectionally to the other frames, by employing the global and local transfer modules. The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the target frame. By applying A-Net and T-Net alternately, a user can obtain desired segmentation results with minimal efforts. We train the entire network in two stages, by emulating user scribbles and employing an auxiliary loss. Experimental results demonstrate that the proposed interactive video object segmentation algorithm outperforms the state-of-the-art conventional algorithms.
We propose to view non-rigid surface registration as a probabilistic inference problem. Given a target surface, we estimate the posterior distribution of surface registrations. We demonstrate how the posterior distribution can be used to build shape models that generalize better and show how to visualize the uncertainty in the established correspondence. Furthermore, in a reconstruction task, we show how to estimate the posterior distribution of missing data without assuming a fixed point-to-point correspondence.We introduce the closest-point proposal for the Metropolis-Hastings algorithm. Our proposal overcomes the limitation of slow convergence compared to a random-walk strategy. As the algorithm decouples inference from modeling the posterior using a propose-and-verify scheme, we show how to choose different distance measures for the likelihood model.All presented results are fully reproducible using publicly available data and our open-source implementation of the registration framework.
In the past few years, we have witnessed the great progress of image super-resolution (SR) thanks to the power of deep learning. However, a major limitation of the current image SR approaches is that they assume a pre-determined degradation model or kernel, e.g. bicubic, controls the image degradation process. This makes them easily fail to generalize in a real-world or non-ideal environment since the degradation model of an unseen image may not obey the pre-determined kernel used when training the SR model. In this work, we present a simple yet effective zero-shot image super-resolution model. Our zero-shot SR model learns an image-specific super-resolution network (SRN) from a low-resolution input image alone, without relying on external training sets. To circumvent the difficulty caused by the unknown internal degradation model of an image, we propose to learn an image-specific degradation simulation network (DSN) together with our image-specific SRN. Specifically, we exploit the depth information, naturally indicating the scales of local image patches, of an image to extract the unpaired high/low-resolution patch collection to train our networks. According to the benchmark test on four datasets with depth labels or estimated depth maps, our proposed depth guided degradation model learning based image super-resolution (DGDML-SR) achieves visually pleasing results and can outperform the state-of-the-arts in perceptual metrics.
Human-object interaction (HOI) detection is an important task for understanding human activity. Graph structure is appropriate to denote the HOIs in the scene. Since there is an subordination between human and object---human play subjective role and object play objective role in HOI, the relations between homogeneous entities and heterogeneous entities in the scene should also not be equally the same. However, previous graph models regard human and object as the same kind of nodes and do not consider that the messages are not equally the same between different entities. In this work, we address such a problem for HOI task by proposing a heterogeneous graph network that models humans and objects as different kinds of nodes and incorporates intra-class messages between homogeneous nodes and inter-class messages between heterogeneous nodes. In addition, a graph attention mechanism based on the intra-class context and inter-class context is exploited to improve the learning. Extensive experiments on the benchmark datasets V-COCO and HICO-DET verify the effectiveness of our method and demonstrate the importance to extract intra-class and inter-class messages which are not equally the same in HOI detection.
Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Due to the large intra-class variations and cross-modality discrepancy with large amount of sample noise, it is difficult to learn discriminative part features. Existing VI-ReID methods instead tend to learn global representations, which have limited discriminability and weak robustness to noisy images. In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID. We propose an intra-modality weighted-part attention module to extract discriminative part-aggregated features, by imposing the domain knowledge on the part relationship mining. To enhance robustness against noisy samples, we introduce cross-modality graph structured attention to reinforce the representation with the contextual relations across the two modalities. We also develop a parameter-free dynamic dual aggregation learning strategy to adaptively integrate the two components in a progressive joint training manner. Extensive experiments demonstrate that DDAG outperforms the state-of-the-art methods under various settings.
Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent scale and depth ambiguities. Current state-of-the-art methods train fully supervised deep neural networks with 3D ground-truth data. However, acquiring 3D annotations is expensive, typically requiring calibrated multi-view setups or labour intensive manual annotations. While annotations of 2D keypoints are much easier to obtain, how to efficiently leverage such extit{weakly-supervised} data to improve the task of 3D hand pose prediction remains an important open question. The key difficulty stems from the fact that direct application of additional 2D supervision mostly benefits the 2D proxy objective but does little to alleviate the depth and scale ambiguities. Embracing this challenge we propose a set of novel losses that constrain the prediction of a neural network to lie within the range of biomechanically feasible 3D hand configurations. We show by extensive experiments that our proposed constraints significantly reduce the depth ambiguity and allow the network to more effectively leverage additional 2D annotated images. For example, on the challenging freiHAND dataset, using additional 2D annotation without our proposed biomechanical constraints reduces the depth error by only $15\%$, whereas the error is reduced significantly by $50\%$ when the proposed biomechanical constraints are used.
Detecting objects and estimating their viewpoint in images are key tasks of 3D scene understanding. Recent approaches have achieved excellent results on very large benchmarks for object detection and viewpoint estimation. However, performances are still lagging behind for novel object categories with few samples. In this paper, we tackle the problems of few-shot object detection and few-shot viewpoint estimation. We propose a meta-learning framework that can be applied to both tasks, possibly including 3D data. Our models improve the results on objects of novel classes by leveraging on rich feature information originating from base classes with many samples. A simple joint feature embedding module is proposed to make the most of this feature sharing. Despite its simplicity, our method outperforms state-of-the-art methods by a large margin on a range of datasets, including PASCAL VOC and MS COCO for few-shot object detection, and Pascal3D+ and ObjectNet3D for few-shot viewpoint estimation. And for the first time, we tackle the combination of both few-shot tasks, on ObjectNet3D, showing promising results.
We consider universal adversarial patches for faces --- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initialization, locations, scales of patches, backbones, and state-of-the-art face detection frameworks. We propose new optimization-based approaches to automatic design of universal adversarial patches for varying goals of the attack, including scenarios in which true positives are suppressed without introducing false positives. Our proposed algorithms perform well on real-world datasets, deceiving state-of-the-art face detectors in terms of multiple precision/recall metrics and transferability.
Due to the ubiquity of smartphones, it is popular to take photos of one's self, or ""selfies."" Such photos are convenient to take, because they do not require specialized equipment or a third-party photographer. However, in selfies, constraints such as human arm length often make the body pose look unnatural. To address this issue, we introduce unselfie, a novel photographic transformation that automatically translates a selfie into a neutral-pose portrait. To achieve this, we first collect an unpaired dataset, and introduce a way to synthesize paired training data for self-supervised learning. Then, to unselfie a photo, we propose a new three-stage pipeline, where we first find a target neutral pose, inpaint the body texture, and finally refine and composite the person on the background. To obtain a suitable target neutral pose, we propose a novel nearest pose search module that makes the reposing task easier and enables the generation of multiple neural-pose results among which users can choose the best one they like. Qualitative and quantitative evaluations show the superiority of our pipeline over alternatives.
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
PDF ↗The advances over the past several years have pushed the performance of face recognition to an amazing level. This great success, to a large extent, is built on top of millions of annotated samples. However, as we endeavor to take the performance to the next level, the reliance on annotated data becomes a major obstacle. We desire to explore an alternative approach, namely using captioned images for training, as an attempt to mitigate this difficulty. Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images. Hence, an effective method to leverage such data would significantly reduce the need of human annotations. However, an important challenge along this way needs to be tackled: the names in the captions are often noisy and ambiguous, especially when there are multiple names in the captions or multiple people in the photos. In this work, we propose a simple yet effective method, which trains a face recognition model by progressively expanding the labeled set via both selective propagation and caption-driven expansion. We build a large-scale dataset of captioned images, which contain 6.3M faces from 305K subjects. Our experiments show that using the proposed method, we can train a state-of-the-art face recognition model without manual annotation (99.65% in LFW). This shows the great potential of caption-supervised face recognition.
Adversarial attacks are valuable for providing insights into the blind-spots of deep learning models and help improve their robustness. Existing work on adversarial attacks have mainly focused on static scenes; however, it remains unclear whether such attacks are effective against embodied agents, which could navigate and interact with a dynamic environment. In this work, we take the first step to study adversarial attacks for embodied agents. In particular, we generate spatiotemporal perturbations to form 3D adversarial examples, which exploit the interaction history in both the temporal and spatial dimensions. Regarding the temporal dimension, since agents make predictions based on historical observations, we develop a trajectory attention module to explore scene view contributions, which further help localize 3D objects appeared with highest stimuli. By conciliating with clues from the temporal dimension, along the spatial dimension, we adversarially perturb the physical properties (e.g., texture and 3D shape) of the contextual objects that appeared in the most important scene views. Extensive experiments on the EQA-v1 dataset for several embodied tasks in both the white-box and black-box settings have been conducted, which demonstrate that our perturbations have strong attack and generalization abilities.
During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the wealth of information on the geometry of the weight space, accumulated over the descent towards the minimum is discarded. In this work we propose to make use of this knowledge and leverage it for computing the distributions of the weights of the DNN. This can be further used for estimating the epistemic uncertainty of the DNN by aggregating predictions from an ensemble of networks sampled from these distributions. To this end we introduce a method for tracking the trajectory of the weights during optimization, that does neither require any change in the architecture, nor in the training procedure. We evaluate our method, TRADI, on standard classification and regression benchmarks, and on out-of-distribution detection for classification and semantic segmentation. We achieve competitive results, while preserving computational efficiency in comparison to ensemble approaches.
Recent pedestrian detection methods generally rely on additional supervision, such as visible bounding-box annotations, to handle heavy occlusions. We propose an approach that leverages pedestrian count and proposal similarity information within a two-stage pedestrian detection framework. Both pedestrian count and proposal similarity are derived from standard full-body annotations commonly used to train pedestrian detectors. We introduce a count-weighted detection loss function that assigns higher weights to the detection errors occurring at highly overlapping pedestrians. The proposed loss function is utilized at both stages of the two-stage detector. We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity. Lastly, we introduce a count and similarity-aware NMS strategy to identify distinct proposals. Our approach requires neither part information nor visible bounding-box annotations. Experiments are performed on the CityPersons and CrowdHuman datasets. Our method sets a new state-of-the-art on both datasets. Further, it achieves an absolute gain of 2.4\% over the current state-of-the-art, in terms of log-average miss rate, on the heavily occluded ( extbf{HO}) set of CityPersons test set. Finally, we demonstrate the applicability of our approach for the problem of human instance segmentation. Code and models are available at: https://github.com/Leotju/CaSe .
In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules, however. In this paper, we propose a light-weight integration between the two schema. We present Attentive Normalization (AN). Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging channel-wise feature attention. In experiments, we test the proposed AN using four representative neural architectures (ResNets, DenseNets, MobileNets-v2 and AOGNets) in the ImageNet-1000 classification benchmark and the MS-COCO 2017 object detection and instance segmentation benchmark. AN obtains consistent performance improvement for different neural architectures in both benchmarks with absolute increase of top-1 accuracy in ImageNet-1000 between 0.5% and 2.7%, and absolute increase up to 1.8% and 2.2% for bounding box and mask AP in MS-COCO respectively. We observe that the proposed AN provides a strong alternative to the widely used Squeeze-and-Excitation (SE) module. Our reproducible source code is publicly available.