论文检索

Guangyao Chen, Peixi Peng, Li Ma, Jia Li, Lin Du, Yonghong Tian

Recently, the generalization behavior of Convolutional Neural Networks (CNN) is gradually transparent through explanation techniques with the frequency components decomposition. However, the importance of the phase spectrum of the image for a robust vision system is still ignored. In this paper, we notice that the CNN tends to converge at the local optimum which is closely related to the high-frequency components of the training images, while the amplitude spectrum is easily disturbed such as noises or common corruptions. In contrast, more empirical studies found that humans rely on more phase components to achieve robust recognition. This observation leads to more explanations of the CNN's generalization behaviors in both robustness to common perturbations and out-of-distribution detection, and motivates a new perspective on data augmentation designed by re-combing the phase spectrum of the current image and the amplitude spectrum of the distracter image. That is, the generated samples force the CNN to pay more attention to the structured information from phase components and keep robust to the variation of the amplitude. Experiments on several image datasets indicate that the proposed method achieves state-of-the-art performances on multiple generalizations and calibration tasks, including adaptability for common corruptions and surface variations, out-of-distribution detection, and adversarial attack.

Jisoo Mok, Byunggook Na, Hyeokjun Choe, Sungroh Yoon

Deep neural networks continue to awe the world with their remarkable performance. Their predictions, however, are prone to be corrupted by adversarial examples that are imperceptible to humans. Current efforts to improve the robustness of neural networks against adversarial examples are focused on developing robust training methods, which update the weights of a neural network in a more robust direction. In this work, we take a step beyond training of the weight parameters and consider the problem of designing an adversarially robust neural architecture with high intrinsic robustness. We propose AdvRush, a novel adversarial robustness-aware neural architecture search algorithm, based upon a finding that independent of the training method, the intrinsic robustness of a neural network can be represented with the smoothness of its input loss landscape. Through a regularizer that favors a candidate architecture with a smoother input loss landscape, AdvRush successfully discovers an adversarially robust neural architecture. Along with a comprehensive theoretical motivation for AdvRush, we conduct an extensive amount of experiments to demonstrate the efficacy of AdvRush on various benchmark datasets. Notably, on CIFAR-10, AdvRush achieves 55.91% robust accuracy under FGSM attack after standard training and 50.04% robust accuracy under AutoAttack after 7-step PGD adversarial training.

Ruixing Wang, Xiaogang Xu, Chi-Wing Fu, Jiangbo Lu, Bei Yu, Jiaya Jia

Low-light video enhancement is an important task. Previous work is mostly trained on paired static images or videos. We compile a new dataset formed by our new strategy that contains high-quality spatially-aligned video pairs from dynamic scenes in low- and normal-light conditions. We built it using a mechatronic system to precisely control the dynamics during the video capture process, and further align the video pairs, both spatially and temporally, by identifying the system's uniform motion stage. Besides the dataset, we propose an end-to-end framework, in which we design a self-supervised strategy to reduce noise, while enhancing the illumination based on the Retinex theory. Extensive experiments based on various metrics and large-scale user study demonstrate the value of our dataset and effectiveness of our method. The dataset and code are available at https://github.com/dvlab-research/SDSD.

Tao Liang, Guosheng Lin, Lei Feng, Yan Zhang, Fengmao Lv

Videos flow as the mixture of language, acoustic, and vision modalities. A thorough video understanding needs to fuse time-series data of different modalities for prediction. Due to the variable receiving frequency for sequences from each modality, there usually exists inherent asynchrony across the collected multimodal streams. Towards an efficient multimodal fusion from asynchronous multimodal streams, we need to model the correlations between elements from different modalities. The recent Multimodal Transformer (MulT) approach extends the self-attention mechanism of the original Transformer network to learn the crossmodal dependencies between elements. However, the direct replication of self-attention will suffer from the distribution mismatch across different modality features. As a result, the learnt crossmodal dependencies can be unreliable. Motivated by this observation, this work proposes the Modality-Invariant Crossmodal Attention (MICA) approach towards learning crossmodal interactions over modality-invariant space in which the distribution mismatch between different modalities is well bridged. To this end, both the marginal distribution and the elements with high-confidence correlations are aligned over the common space of the query and key vectors which are computed from different modalities. Experiments on three standard benchmarks of multimodal video understanding clearly validate the superiority of our approach.

Minghao Xu, Hang Wang, Bingbing Ni, Riheng Zhu, Zhenbang Sun, Changhu Wang

Autonomous highlight detection is crucial for enhancing the efficiency of video browsing on social media platforms. To attain this goal in a data-driven way, one may often face the situation where highlight annotations are not available on the target video category used in practice, while the supervision on another video category (named as source video category) is achievable. In such a situation, one can derive an effective highlight detector on target video category by transferring the highlight knowledge acquired from source video category to the target one. We call this problem cross-category video highlight detection, which has been rarely studied in previous works. For tackling such practical problem, we propose a Dual-Learner-based Video Highlight Detection (DL-VHD) framework. Under this framework, we first design a Set-based Learning module (SL-module) to improve the conventional pair-based learning by assessing the highlight extent of a video segment under a broader context. Based on such learning manner, we introduce two different learners to acquire the basic distinction of target category videos and the characteristics of highlight moments on source video category, respectively. These two types of highlight knowledge are further consolidated via knowledge distillation. Extensive experiments on three benchmark datasets demonstrate the superiority of the proposed SL-module, and the DL-VHD method outperforms five typical Unsupervised Domain Adaptation (UDA) algorithms on various cross-category highlight detection tasks.

Heewon Kim, Sungyong Baik, Myungsub Choi, Janghoon Choi, Kyoung Mu Lee

We present a novel framework for controllable image restoration that can effectively restore multiple types and levels of degradation of a corrupted image. The proposed model, named TASNet, is automatically determined by our neural architecture search algorithm, which optimizes the efficiency-accuracy trade-off of the candidate model architectures. Specifically, we allow TASNet to share the early layers across different restoration tasks and adaptively adjust the remaining layers with respect to each task. The shared task-agnostic layers greatly improve the efficiency while the task-specific layers are optimized for restoration quality, and our search algorithm seeks for the best balance between the two. We also propose a new data sampling strategy to further improve the overall restoration performance. As a result, TASNet achieves significantly faster GPU latency and lower FLOPs compared to the existing state-of-the-art models, while also showing visually more pleasing outputs. The source code and pre-trained models are available at https://github.com/ghimhw/TASNet.

Xiao Tang, Tianyu Wang, Chi-Wing Fu

3D hand-mesh reconstruction from RGB images facilitates many applications, including augmented reality (AR). However, this requires not only real-time speed and accurate hand pose and shape but also plausible mesh-image alignment. While existing works already achieve promising results, meeting all three requirements is very challenging. This paper presents a novel pipeline by decoupling the hand-mesh reconstruction task into three stages: a joint stage to predict hand joints and segmentation; a mesh stage to predict a rough hand mesh; and a refine stage to fine-tune it with an offset mesh for mesh-image alignment. With careful design in the network structure and in the loss functions, we can promote high-quality finger-level mesh-image alignment and drive the models together to deliver real-time predictions. Extensive quantitative and qualitative results on benchmark datasets demonstrate that the quality of our results outperforms the state-of-the-art methods on hand-mesh/pose precision and hand-image alignment. In the end, we also showcase several real-time AR scenarios.

Peixian Chen, Wenfeng Liu, Pingyang Dai, Jianzhuang Liu, Qixiang Ye, Mingliang Xu, Qi’an Chen, Rongrong Ji

Person Re-Identification (ReID) has achieved remarkable performance along with the deep learning era. However, most approaches carry out ReID only based upon holistic pedestrian regions. In contrast, real-world scenarios involve occluded pedestrians, which provide partial visual appearances and destroy the ReID accuracy. A common strategy is to locate visible body parts by auxiliary model, which however suffers from significant domain gaps and data bias issues. To avoid such problematic models in occluded person ReID, we propose the Occlusion-Aware Mask Network (OAMN). In particular, we incorporate an attention-guided mask module, which requires guidance from labeled occlusion data. To this end, we propose a novel occlusion augmentation scheme that produces diverse and precisely labeled occlusion for any holistic dataset. The proposed scheme suits real-world scenarios better than existing schemes, which consider only limited types of occlusions. We also offer a novel occlusion unification scheme to tackle ambiguity information at the test phase. The above three components enable existing attention mechanisms to precisely capture body parts regardless of the occlusion. Comprehensive experiments on a variety of person ReID benchmarks demonstrate the superiority of OAMN over state-of-the-arts.

Jiwoong Choi, Ismail Elezi, Hyuk-Jae Lee, Clement Farabet, Jose M. Alvarez

Active learning aims to reduce labeling costs by selecting only the most informative samples on a dataset. Few existing works have addressed active learning for object detection. Most of these methods are based on multiple models or are straightforward extensions of classification methods, hence estimate an image's informativeness using only the classification head. In this paper, we propose a novel deep active learning approach for object detection. Our approach relies on mixture density networks that estimate a probabilistic distribution for each localization and classification head's output. We explicitly estimate the aleatoric and epistemic uncertainty in a single forward pass of a single model. Our method uses a scoring function that aggregates these two types of uncertainties for both heads to obtain every image's informativeness score. We demonstrate the efficacy of our approach in PASCAL VOC and MS-COCO datasets. Our approach outperforms single-model based methods and performs on par with multi-model based methods at a fraction of the computing cost.

Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao

Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples. Existing methods suffer the problem of feature undermining, i.e. potential novel classes are treated as background during training phase. Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes. In our work, we propose a novel joint-training framework. Based on conventional episodic training on support-query pairs, we add an additional mining branch that exploits latent novel classes via transferable sub-clusters, and a new rectification technique on both background and foreground categories to enforce more stable prototypes. Over and above that, our transferable sub-cluster has the ability to leverage extra unlabeled data for further feature enhancement. Extensive experiments on two FSS benchmarks demonstrate that our method outperforms previous state-of-the-art by a large margin of 3.7% mIOU on PASCAL-5i and 7.0% mIOU on COCO-20i at the cost of 74% fewer parameters and 2.5x faster inference speed. The source code is available at https://github.com/LiheYoung/MiningFSS.

Minghao Chen, Houwen Peng, Jianlong Fu, Haibin Ling

Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding dimension, and number of heads can largely affect the performance of vision transformers. Previous models configure these dimensions based upon manual crafting. In this work, we propose a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search. AutoFormer entangles the weights of different blocks in the same layers during supernet training. Benefiting from the strategy, the trained supernet allows thousands of subnets to be very well-trained. Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch. Besides, the searched models, which we refer to AutoFormers, surpass the recent state-of-the-arts such as ViT and DeiT. In particular, AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively. Lastly, we verify the transferability of AutoFormer by providing the performance on downstream benchmarks and distillation experiments. Code and models are available at https://github.com/microsoft/Cream.

Huili Chen, Cheng Fu, Jishen Zhao, Farinaz Koushanfar

The security of Deep Neural Networks (DNNs) is of great importance due to their employment in various safety-critical applications. DNNs are shown to be vulnerable against the Trojan attack that manipulates the model parameters via poisoned training and gets activated by the pre-defined trigger in inputs during inference. In this work, we present ProFlip, the first targeted Trojan attack framework that can divert the prediction of the DNN to the target class by progressively identifying and flipping a small set of bits in model parameters. At its core, ProFlip consists of three key phases: (i) Determining significant neurons in the last layer; (ii) Generating an effective trigger pattern for the target class; (iii) Identifying a sequence of susceptible bits of DNN parameters stored in the main memory (e.g., DRAM). After model deployment, the adversary can insert the Trojan by flipping the critical bits found by ProFlip using bit flip techniques such as Row Hammer or laser beams. As the result, the altered DNN predicts the target class when the trigger pattern is present in any inputs. We perform extensive evaluations of ProFlip on CIFAR10, SVHN, and ImageNet datasets with ResNet-18 and VGG-16 architectures. Empirical results show that, to reach an attack success rate (ASR) of over 94%, ProFlip requires only 12 bit flips out of 88 million parameter bits for ResNet-18 with CIFAR-10, and 15 bit flips for ResNet-18 with ImageNet. Compared to the SOTA, ProFlip reduces the number of required bits flips by 28x 34x while reaching the same level of ASR.

Mengyu Dai, Haibin Hang

We propose a manifold matching approach to generative models which includes a distribution generator (or data generator) and a metric generator. In our framework, we view the real data set as some manifold embedded in a high-dimensional Euclidean space. The distribution generator aims at generating samples that follow some distribution condensed around the real data manifold. It is achieved by matching two sets of points using their geometric shape descriptors, such as centroid and p-diameter, with learned distance metric; the metric generator utilizes both real data and generated samples to learn a distance metric which is close to some intrinsic geodesic distance on the real data manifold. The produced distance metric is further used for manifold matching. The two networks learn simultaneously during the training process. We apply the approach on both unsupervised and supervised learning tasks: in unconditional image generation task, the proposed method obtains competitive results compared with existing generative models; in super-resolution task, we incorporate the framework in perception-based models and improve visual qualities by producing samples with more natural textures. Experiments and analysis demonstrate the feasibility and effectiveness of the proposed framework.

Frederik Warburg, Martin Jørgensen, Javier Civera, Søren Hauberg

Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem. Current methods for estimating uncertainties are poorly calibrated, computationally expensive, or based on heuristics. We present a new method that views image embeddings as stochastic features rather than deterministic features. Our two main contributions are (1) a likelihood that matches the triplet constraint and that evaluates the probability of an anchor being closer to a positive than a negative; and (2) a prior over the feature space that justifies the conventional l2 normalization. To ensure computational efficiency, we derive a variational approximation of the posterior, called the Bayesian triplet loss, that produces state-of-the-art uncertainty estimates and matches the predictive performance of current state-of-the-art methods.

Fanglei Xue, Qiangchang Wang, Guodong Guo

Facial expression recognition (FER) has received increasing interest in computer vision. We propose the TransFER model which can learn rich relation-aware local representations. It mainly consists of three components: Multi-Attention Dropping (MAD), ViT-FER, and Multi-head Self-Attention Dropping (MSAD). First, local patches play an important role in distinguishing various expressions, however, few existing works can locate discriminative and diverse local patches. This can cause serious problems when some patches are invisible due to pose variations or viewpoint changes. To address this issue, the MAD is proposed to randomly drop an attention map. Consequently, models are pushed to explore diverse local patches adaptively. Second, to build rich relations between different local patches, the Vision Transformers (ViT) are used in FER, called ViT-FER. Since the global scope is used to reinforce each local patch, a better representation is obtained to boost the FER performance. Thirdly, the multi-head self-attention allows ViT to jointly attend to features from different information subspaces at different positions. Given no explicit guidance, however, multiple self-attentions may extract similar relations. To address this, the MSAD is proposed to randomly drop one self-attention module. As a result, models are forced to learn rich relations among diverse local patches. Our proposed TransFER model outperforms the state-of-the-art methods on several FER benchmarks, showing its effectiveness and usefulness.

Lei Ke, Yu-Wing Tai, Chi-Keung Tang

Conventional video inpainting is neither object-oriented nor occlusion-aware, making it liable to obvious artifacts when large occluded object regions are inpainted. This paper presents occlusion-aware video object inpainting, which recovers both the complete shape and appearance for occluded objects in videos given their visible mask segmentation. To facilitate this new research, we construct the first large-scale video object inpainting benchmark YouTube-VOI to provide realistic occlusion scenarios with both occluded and visible object masks available. Our technical contribution VOIN jointly performs video object shape completion and occluded texture generation. In particular, the shape completion module models long-range object coherence while the flow completion module recovers accurate flow with sharp motion boundary, for propagating temporally-consistent texture to the same moving object across frames. For more realistic results, VOIN is optimized using both T-PatchGAN and a new spatio-temporal attention-based multi-class discriminator. Finally, we compare VOIN and strong baselines on YouTube-VOI. Experimental results clearly demonstrate the efficacy of our method including inpainting complex and dynamic objects. VOIN degrades gracefully with inaccurate input visible mask.

Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios. It is therefore tricky to decide which learning strategies to use under different task conditions. Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs. The goal of our work is to search for good parameter adaptation policies that are applied to different stages in the network for few-shot classification. We present a search space that covers many popular few-shot learning algorithms in the literature and develop a differentiable searching and decoding algorithm based on meta-learning that supports gradient-based optimization. We demonstrate the effectiveness of our searching-based method on multiple benchmark datasets. Extensive experiments show that our approach significantly outperforms baselines and demonstrates performance advantages over many state-of-the-art methods. Code and models will be made publicly available.

Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further improve the quality of different objects, we create a bank of Generative Adversarial Networks (GANs) by separately training class-specific models. This has several benefits including -- dedicated weights for each class; centrally aligned data for each model; additional training data from other sources, potential of higher resolution and quality; and easy manipulation of a specific object in the scene. Experiments show that our approach can generate high quality images in high resolution while having flexibility of object-level control by using class-specific generators.

Rui Gong, Dengxin Dai, Yuhua Chen, Wen Li, Luc Van Gool

One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities. This necessitates methods to combine and reuse existing datasets that may belong to different domains, have partial annotations, and/or have different data modalities. This paper formulates this as a multi-source domain adaptation and label unification problem, and proposes a novel method for it. Our method consists of a partially-supervised adaptation stage and a fully-supervised adaptation stage. In the former, partial knowledge is transferred from multiple source domains to the target domain and fused therein. Negative transfer between unmatching label spaces is mitigated via three new modules: domain attention, uncertainty maximization and attention-guided adversarial alignment. In the latter, knowledge is transferred in the unified label space after a label completion process with pseudo-labels. Extensive experiments on three different tasks - image classification, 2D semantic image segmentation, and joint 2D-3D semantic segmentation - show that our method outperforms all competing methods significantly.

Yingbin Bai, Tongliang Liu

Examples that are close to the decision boundary---that we term hard examples, are essential to shape accurate classifiers. Extracting confident examples has been widely studied in the community of learning with noisy labels. However, it remains elusive how to extract hard confident examples from the noisy training data. In this paper, we propose a deep learning paradigm to solve this problem, which is built on the memorization effect of deep neural networks that they would first learn simple patterns, i.e., which are defined by these shared by multiple training examples. To extract hard confident examples that contain non-simple patterns and are entangled with the inaccurately labeled examples, we borrow the idea of momentum from physics. Specifically, we alternately update the confident examples and refine the classifier. Note that the extracted confident examples in the previous round can be exploited to learn a better classifier and that the better classifier will help identify better (and hard) confident examples. We call the approach the "Momentum of Memorization" (Me-Momentum). Empirical results on benchmark-simulated and real-world label-noise data illustrate the effectiveness of Me-Momentum for extracting hard confident examples, leading to better classification performance.