CVPR 2020 论文列表

This work presents an efficient yet effective online Knowledge Distillation method via Collaborative Learning, termed KDCL, which is able to consistently improve the generalization ability of deep neural networks (DNNs) that have different learning capacities. Unlike existing two-stage knowledge distillation approaches that pre-train a DNN with large capacity as the "teacher" and then transfer the teacher's knowledge to another "student" DNN unidirectionally (i.e. one-way), KDCL treats all DNNs as "students" and collaboratively trains them in a single stage (knowledge is transferred among arbitrary students during collaborative training), enabling parallel computing, fast computations, and appealing generalization ability. Specifically, we carefully design multiple methods to generate soft target as supervisions by effectively ensembling predictions of students and distorting the input images. Extensive experiments show that KDCL consistently improves all the "students" on different datasets, including CIFAR-100 and ImageNet. For example, when trained together by using KDCL, ResNet-50 and MobileNetV2 achieve 78.2% and 74.0% top-1 accuracy on ImageNet, outperforming the original results by 1.4% and 2.0% respectively. We also verify that models pre-trained with KDCL transfer well to object detection and semantic segmentation on MS COCO dataset. For instance, the FPN detector is improved by 0.9% mAP.

Person Re-IDentification (P-RID), as an instance-level recognition problem, still remains challenging in computer vision community. Many P-RID works aim to learn faithful and discriminative features/metrics from offline training data and directly use them for the unseen online testing data. However, their performance is largely limited due to the severe data shifting issue between training and testing data. Therefore, we propose an online joint multi-metric adaptation model to adapt the offline learned P-RID models for the online data by learning a series of metrics for all the sharing-subsets. Each sharing-subset is obtained from the proposed novel frequent sharing-subset mining module and contains a group of testing samples which share strong visual similarity relationships to each other. Unlike existing online P-RID methods, our model simultaneously takes both the sample-specific discriminant and the set-based visual similarity among testing samples into consideration so that the adapted multiple metrics can refine the discriminant of all the given testing samples jointly via a multi-kernel late fusion framework. Our proposed model is generally suitable to any offline learned P-RID baselines for online boosting, the performance improvement by our model is not only verified by extensive experiments on several widely-used P-RID benchmarks (CUHK03, Market1501, DukeMTMC-reID and MSMT17) and state-of-the-art P-RID baselines but also guaranteed by the provided in-depth theoretical analyses.

Online depth learning is the problem of consistently adapting a depth estimation model to handle a continuously changing environment. This problem is challenging due to the network easily overfits on the current environment and forgets its past experiences. To address such problem, this paper presents a novel Learning to Prevent Forgetting (LPF) method for online mono-depth adaptation to new target domains in unsupervised manner. Instead of updating the universal parameters, LPF learns adapter modules to efficiently adjust the feature representation and distribution without losing the pre-learned knowledge in online condition. Specifically, to adapt temporal-continuous depth patterns in videos, we introduce a novel meta-learning approach to learn adapter modules by combining online adaptation process into the learning objective. To further avoid overfitting, we propose a novel temporal-consistent regularization to harmonize the gradient descent procedure at each online learning step. Extensive evaluations on real-world datasets demonstrate that the proposed method, with very limited parameters, significantly improves the estimation quality.

Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature clustering and network parameters update leads to unstable learning of visual representations. To overcome this challenge, we propose Online Deep Clustering (ODC) that performs clustering and network update simultaneously rather than alternatingly. Our key insight is that the cluster centroids should evolve steadily in keeping the classifier stably updated. Specifically, we design and maintain two dynamic memory modules, i.e., samples memory to store samples' labels and features, and centroids memory for centroids evolution. We break down the abrupt global clustering into steady memory update and batch-wise label re-assignment. The process is integrated into network update iterations. In this way, labels and the network evolve shoulder-to-shoulder rather than alternatingly. Extensive experiments demonstrate that ODC stabilizes the training process and boosts the performance effectively.

In this paper, we propose a framework capable of generating face images that fall into the same distribution as that of a given one-shot example. We leverage a pre-trained StyleGAN model that already learned the generic face distribution. Given the one-shot target, we develop an iterative optimization scheme that rapidly adapts the weights of the model to shift the output's high-level distribution to the target's. To generate images of the same distribution, we introduce a style-mixing technique that transfers the low-level statistics from the target to faces randomly generated with the model. With that, we are able to generate an unlimited number of faces that inherit from the distribution of both generic human faces and the one-shot example. The newly generated faces can serve as augmented training data for other downstream tasks. Such setting is appealing as it requires labeling very few, or even one example, in the target domain, which is often the case of real-world face manipulations that result from a variety of unknown and unique distributions, each with extremely low prevalence. We show the effectiveness of our one-shot approach for detecting face manipulations and compare it with other few-shot domain adaptation methods qualitatively and quantitatively.

Almost all adversarial attacks in computer vision are aimed at pre-known object categories, which could be offline trained for generating perturbations. But as for visual object tracking, the tracked target categories are normally unknown in advance. However, the tracking algorithms also have potential risks of being attacked, which could be maliciously used to fool the surveillance systems. Meanwhile, it is still a challenging task that adversarial attacks on tracking since it has the free-model tracked target. Therefore, to help draw more attention to the potential risks, we study adversarial attacks on tracking algorithms. In this paper, we propose a novel one-shot adversarial attack method to generate adversarial examples for free-model single object tracking, where merely adding slight perturbations on the target patch in the initial frame causes state-of-the-art trackers to lose the target in subsequent frames. Specifically, the optimization objective of the proposed attack consists of two components and leverages the dual attention mechanisms. The first component adopts a targeted attack strategy by optimizing the batch confidence loss with confidence attention while the second one applies a general perturbation strategy by optimizing the feature loss with channel attention. Experimental results show that our approach can significantly lower the accuracy of the most advanced Siamese network-based trackers on three benchmarks.

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against adversarial examples, a plausible idea is to obfuscate the network's gradient with respect to the input image. This general idea has inspired a long line of defense methods. Yet, almost all of them have proven vulnerable. We revisit this seemingly flawed idea from a radically different perspective. We embrace the omnipresence of adversarial examples and the numerical procedure of crafting them, and turn this harmful attacking process into a useful defense mechanism. Our defense method is conceptually simple: before feeding an input image for classification, transform it by finding an adversarial example on a pre-trained external model. We evaluate our method against a wide range of possible attacks. On both CIFAR-10 and Tiny ImageNet datasets, our method is significantly more robust than state-of-the-art methods. Particularly, in comparison to adversarial training, our method offers lower training cost as well as stronger robustness.

Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.

Dropout and its extensions (e.g. DropBlock and DropConnect) are popular heuristics for training neural networks, which have been shown to improve generalization performance in practice. However, a theoretical understanding of their optimization and regularization properties remains elusive. Recent work shows that in the case of single hidden-layer linear networks, Dropout is a stochastic gradient descent method for minimizing a regularized loss, and that the regularizer induces solutions that are low-rank and balanced. In this work we show that for single hidden-layer linear networks, DropBlock induces spectral k-support norm regularization, and promotes solutions that are low-rank and have factors with equal norm. We also show that the global minimizer for DropBlock can be computed in closed form, and that DropConnect is equivalent to Dropout. We then show that some of these results can be extended to a general class of Dropout-strategies, and, with some assumptions, to deep non-linear networks when Dropout is applied to the last layer. We verify our theoretical claims and assumptions experimentally with commonly used network architectures.

Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are vulnerable to learning coincidental correlations in the data rather than deeper relations between image content and ideas expressed in language. We present a dataset that takes a step towards addressing this problem in that it contains questions expressed in two languages, and an evaluation process that co-opts a well understood image-based metric to reflect the method's ability to reason. Measuring reasoning directly encourages generalization by penalizing answers that are coincidentally correct. The dataset reflects the scene-text version of the VQA problem, and the reasoning evaluation can be seen as a text-based version of a referring expression challenge. Experiments and analyses are provided that show the value of the dataset. The dataset is available at www.est-vqa.org.

Rotation Averaging is a non-convex optimization problem that determines orientations of a collection of cameras from their images of a 3D scene. The problem has been studied using a variety of distances and robustifiers. The intrinsic (or geodesic) distance on SO(3) is geometrically meaningful; but while some extrinsic distance-based solvers admit (conditional) guarantees of correctness, no comparable results have been found under the intrinsic metric. In this paper, we study the spatial distribution of local minima. First, we do a novel empirical study to demonstrate sharp transitions in qualitative behavior: as problems become noisier, they transition from a single (easy-to-find) dominant minimum to a cost surface filled with minima. In the second part of this paper we derive a theoretical bound for when this transition occurs. This is an extension of the results of [24], which used local convexity as a proxy to study the difficulty of problem. By recognizing the underly- ing quotient manifold geometry of the problem we achieve an n-fold improvement over prior work. Incidentally, our analysis also extends the prior l2 work to general lp costs. Our results suggest using algebraic connectivity as an indicator of problem difficulty.

Detecting manipulated facial images and videos is an increasingly important topic in digital media forensics. As advanced face synthesis and manipulation methods are made available, new types of fake face representations are being created which have raised significant concerns for their use in social media. Hence, it is crucial to detect manipulated face images and localize manipulated regions. Instead of simply using multi-task learning to simultaneously detect manipulated images and predict the manipulated mask (regions), we propose to utilize an attention mechanism to process and improve the feature maps for the classification task. The learned attention maps highlight the informative regions to further improve the binary classification (genuine face v. fake face), and also visualize the manipulated regions. To enable our study of manipulated face detection and localization, we collect a large-scale database that contains numerous types of facial forgeries. With this dataset, we perform a thorough analysis of data-driven fake face detection. We show that the use of an attention mechanism improves facial forgery detection and manipulated region localization.

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward locking, backward locking, and update locking problems. Existing solutions for acceleration either can only handle one locking problem or lead to severe accuracy loss or memory inefficiency. Moreover, none of them consider the straggler problem among devices. In this paper, we propose Layer-wise Staleness and a novel efficient training algorithm, Diversely Stale Parameters (DSP), to address these challenges. We also analyze the convergence of DSP with two popular gradient-based methods and prove that both of them are guaranteed to converge to critical points for non-convex problems. Finally, extensive experimental results on training deep learning models demonstrate that our proposed DSP algorithm can achieve significant training speedup with stronger robustness than compared methods.

The pursuit of high performance on public benchmarks has been the driving force for research in scene text recognition, and notable progresses have been achieved. However, a close investigation reveals a startling fact that the state-of-the-art methods perform well on images with words within vocabulary but generalize poorly to images with words outside vocabulary. We call this phenomenon "vocabulary reliance". In this paper, we establish an analytical framework, in which different datasets, metrics and module combinations for quantitative comparisons are devised, to conduct an in-depth study on the problem of vocabulary reliance in scene text recognition. Key findings include: (1) Vocabulary reliance is ubiquitous, i.e., all existing algorithms more or less exhibit such characteristic; (2) Attention-based decoders prove weak in generalizing to words outside vocabulary and segmentation-based decoders perform well in utilizing visual features; (3) Context modeling is highly coupled with the prediction layers. These findings provide new insights and can benefit future research in scene text recognition. Furthermore, we propose a simple yet effective mutual learning strategy to allow models of two families (attention-based and segmentation-based) to learn collaboratively. This remedy alleviates the problem of vocabulary reliance and significantly improves the overall scene text recognition performance.

In this paper we challenge the common assumption that convolutional layers in modern CNNs are translation invariant. We show that CNNs can and will exploit the absolute spatial location by learning filters that respond exclusively to particular absolute locations by exploiting image boundary effects. Because modern CNNs filters have a huge receptive field, these boundary effects operate even far from the image boundary, allowing the network to exploit absolute spatial location all over the image. We give a simple solution to remove spatial location encoding which improves translation invariance and thus gives a stronger visual inductive bias which particularly benefits small data sets. We broadly demonstrate these benefits on several architectures and various applications such as image classification, patch matching, and two video classification datasets.

This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification criterion was kept fixed all through the learning process of the discriminator without considering the gradually improved quality of generated data, even if they could be more realistic than real data at times. In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality. The discriminator is thus a classifier for this positive and unlabeled classification problem, and we derive a new Positive-Unlabeled GAN (PUGAN). We theoretically discuss the global optimality the proposed model will achieve and the equivalent optimization goal. Empirically, we find that PUGAN can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.

We propose a novel formulation for joint recovery of camera pose, object geometry and spatially-varying BRDF. The input to our approach is a sequence of RGB-D images captured by a mobile, hand-held scanner that actively illuminates the scene with point light sources. Compared to previous works that jointly estimate geometry and materials from a hand-held scanner, we formulate this problem using a single objective function that can be minimized using off-the-shelf gradient-based solvers. By integrating material clustering as a differentiable operation into the optimization process, we avoid pre-processing heuristics and demonstrate that our model is able to determine the correct number of specular materials independently. We provide a study on the importance of each component in our formulation and on the requirements of the initial geometry. We show that optimizing over the poses is crucial for accurately recovering fine details and show that our approach naturally results in a semantically meaningful material segmentation.

While deep learning in 3D domain has achieved revolutionary performance in many tasks, the robustness of these models has not been sufficiently studied or explored. Regarding the 3D adversarial samples, most existing works focus on manipulation of local points, which may fail to invoke the global geometry properties, like robustness under linear projection that preserves the Euclidean distance, i.e., isometry. In this work, we show that existing state-of-the-art deep 3D models are extremely vulnerable to isometry transformations. Armed with the Thompson Sampling, we develop a black-box attack with success rate over 95% on ModelNet40 data set. Incorporating with the Restricted Isometry Property, we propose a novel framework of white-box attack on top of spectral norm based perturbation. In contrast to previous works, our adversarial samples are experimentally shown to be strongly transferable. Evaluated on a sequence of prevailing 3D models, our white-box attack achieves success rates from 98.88% to 100%. It maintains a successful attack rate over 95% even within an imperceptible rotation range [+-2.81*].

A popular method for anomaly detection is to use the generator of an adversarial network to formulate anomaly score over reconstruction loss of input. Due to the rare occurrence of anomalies, optimizing such networks can be a cumbersome task. Another possible approach is to use both generator and discriminator for anomaly detection. However, attributed to the involvement of adversarial training, this model is often unstable in a way that the performance fluctuates drastically with each training step. In this study, we propose a framework that effectively generates stable results across a wide range of training steps and allows us to use both the generator and the discriminator of an adversarial model for efficient and robust anomaly detection. Our approach transforms the fundamental role of a discriminator from identifying real and fake data to distinguishing between good and bad quality reconstructions. To this end, we prepare training examples for the good quality reconstruction by employing the current generator, whereas poor quality examples are obtained by utilizing an old state of the same generator. This way, the discriminator learns to detect subtle distortions that often appear in reconstructions of the anomaly inputs. Extensive experiments performed on Caltech-256 and MNIST image datasets for novelty detection show superior results. Furthermore, on UCSD Ped2 video dataset for anomaly detection, our model achieves a frame-level AUC of 98.1%, surpassing recent state-of-the-art methods