We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that the transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3xwhile keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention, which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirements, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
User data confidentiality protection is becoming a rising challenge in the present deep learning research. Without access to data, conventional data-driven model compression faces a higher risk of performance degradation. Recently, some works propose to generate images from a specific pretrained model to serve as training data. However, the inversion process only utilizes biased feature statistics stored in one model and is from low-dimension to high-dimension. As a consequence, it inevitably encounters the difficulties of generalizability and inexact inversion, which leads to unsatisfactory performance. To address these problems, we propose MixMix based on two simple yet effective techniques: (1) Feature Mixing: utilizes various models to construct a universal feature space for generalized inversion; (2) Data Mixing: mixes the synthesized images and labels to generate exact label information. We prove the effectiveness of MixMix from both theoretical and empirical perspectives. Extensive experiments show that MixMix outperforms existing methods on the mainstream compression tasks, including quantization, knowledge distillation and pruning. Specifically, MixMix achieves up to 4% and 20% accuracy uplift on quantization and pruning, respectively, compared to existing data-free compression work.
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task. The effect of this type of training on semantic segmentation, contrarily, just commences. We make the initial attempt to explore the defense strategy on semantic segmentation by formulating a general adversarial training procedure that can perform decently on both adversarial and clean samples. We propose a dynamic divide-and-conquer adversarial training (DDC-AT) strategy to enhance the defense effect, by setting additional branches in the target model during training, and dealing with pixels with diverse properties towards adversarial perturbation. Our dynamical division mechanism divides pixels into multiple branches automatically. Note all these additional branches can be abandoned during inference and thus leave no extra parameter and computation cost. Extensive experiments with various segmentation models are conducted on PASCAL VOC 2012 and Cityscapes datasets, in which DDC-AT yields satisfying performance under both white- and black-box attack. The code is available at https://github.com/dvlab-research/Robust-Semantic-Segmentation.
The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses. While prior approaches have successfully created object-centric reconstructions of many scenes, they fail to exploit other structures, such as planes, which are typically the dominant components of indoor scenes. In this paper, we reconstruct planar surfaces from multiple views, while jointly estimating camera pose. Our experiments demonstrate that our method is able to advance the state of the art of reconstruction from sparse views, on challenging scenes from Matterport3D.
Goal-conditioned approaches recently have been found very useful to human trajectory prediction, when adequate goal estimates are provided. Yet, goal inference is difficult in itself and often incurs extra learning efforts. We propose to predict pedestrian trajectories via the guidance of goal expertise, which can be obtained with modest expense through a novel goal-search mechanism on already seen training examples. There are three key contributions in our study. First, we devise a framework that exploits the nearest examples for high-quality goal position inquiry. This approach naturally considers multi-modality, physical constraints, compatibility with existing methods and is model-free; it therefore does not require additional learning efforts typical in goal inference. Second, we present an end-to-end trajectory predictor that can efficiently associate goal retrievals to past motion information and dynamically infer possible future trajectories. Third, with these two novel techniques in hand, we conduct a series of experiments on two broadly explored datasets (SDD and ETH/UCY) and show that our approach surpasses previous state-of-the-art performance by notable margins and reduces the need for additional parameters.
Point cloud segmentation is a fundamental task in 3D. Despite recent progress on point cloud segmentation with the power of deep networks, current deep learning methods based on the clean label assumptions may fail with noisy labels. Yet, object class labels are often mislabeled in real-world point cloud datasets. In this work, we take the lead in solving this issue by proposing a novel Point Noise-Adaptive Learning (PNAL) framework. Compared to existing noise-robust methods on image tasks, our PNAL is noise-rate blind, to cope with the spatially variant noise rate problem specific to point clouds. Specifically, we propose a novel point-wise confidence selection to obtain reliable labels based on the historical predictions of each point. A novel cluster-wise label correction is proposed with a voting strategy to generate the best possible label taking the neighbor point correlations into consideration. We conduct extensive experiments to demonstrate the effectiveness of PNAL on both synthetic and real-world noisy datasets. In particular, even with 60% symmetric noisy labels, our proposed method produces much better results than its baseline counterpart without PNAL and is comparable to the ideal upper bound trained on a completely clean dataset. Moreover, we fully re-labeled the validation set of a popular but noisy real-world scene dataset ScanNetV2 to make it clean, for rigorous experiment and future research. Our code and data will be released.
The core of visual place recognition (VPR) lies in how to identify task-relevant visual cues and embed them into discriminative representations. Focusing on these two points, we propose a novel encoding strategy named Attentional Pyramid Pooling of Salient Visual Residuals (APPSVR). It incorporates three types of attention modules to model the saliency of local features in individual, spatial and cluster dimensions respectively. (1) To inhibit task-irrelevant local features, a semantic-reinforced local weighting scheme is employed for local feature refinement; (2) To leverage the spatial context, an attentional pyramid structure is constructed to adaptively encode regional features according to their relative spatial saliency; (3) To distinguish the different importance of visual clusters to the task, a parametric normalization is proposed to adjust their contribution to image descriptor generation. Experiments demonstrate APPSVR outperforms the existing techniques and achieves a new state-of-the-art performance on VPR benchmark datasets. The visualization shows the saliency map learned in a weakly supervised manner is largely consistent with human cognition.
A Hybrid Frequency-Spatial Domain Model for Sparse Image Reconstruction in Scanning Transmission Electron Microscopy
PDF ↗Scanning transmission electron microscopy (STEM) is a powerful technique in high-resolution atomic imaging of materials. Decreasing scanning time and reducing electron beam exposure with an acceptable signal-to-noise results are two popular research aspects when applying STEM to beam-sensitive materials. Specifically, partially sampling with fixed electron doses is one of the most important solutions, and then the lost information is restored by computational methods. Following successful applications of deep learning in image in-painting, we have developed an encoder-decoder network to reconstruct STEM images in extremely sparse sampling case. In our model, we combine both local pixel information from convolution operators and global texture features, by applying specific filter operations on frequency domain to acquire initial reconstruction and global structure prior. Our method can effectively restore texture structures and be robust in different sampling ratios with Poisson noise. A comprehensive study demonstrates that our method gains about 50% performance enhancement in comparison with the state-of-art methods. Code is available at https://github.com/icthrm/Sparse-Sampling-Reconstruction.
Universal Domain Adaptation (UNDA) aims to handle both domain-shift and category-shift between two datasets, where the main challenge is to transfer knowledge while rejecting "unknown" classes which are absent in the labeled source data but present in the unlabeled target data. Existing methods manually set a threshold to reject "unknown" samples based on validation or a pre-defined ratio of "unknown" samples, but this strategy is not practical. In this paper, we propose a method to learn the threshold using source samples and to adapt it to the target domain. Our idea is that a minimum inter-class distance in the source domain should be a good threshold to decide between "known" or "unknown" in the target. To learn the inter- and intra-class distance, we propose to train a one-vs-all classifier for each class using labeled source data. Then, we adapt the open-set classifier to the target domain by minimizing class entropy. The resulting framework is the simplest of all baselines of UNDA and is insensitive to the value of a hyper-parameter, yet outperforms baselines with a large margin.
Monocular 3D object detection has received increasing attention due to the wide application in autonomous driving. Existing works mainly focus on introducing geometry projection to predict depth priors for each object. Despite their impressive progress, these methods neglect the geometry leverage effect of the projection process, which leads to uncontrollable inferences and damage the training efficiency. In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to handle these problems, which can guide the model to learn more reliable depth outputs. The overall framework combines the uncertainty inference and the hierarchical task learning to reduce the negative effects of the geometry leverage. Specifically, an Uncertainty Geometry Projection module is proposed to obtain the geometry guided uncertainty of the inferred depth, which can not only benefit the geometry learning but also provide more reliable depth inferences to reduce the uncontrollableness caused by the geometry leverage. Besides, to reduce the instability in the training process caused by the geometry leverage effect, we propose a Hierarchical Task Learning strategy to control the overall optimization process. This learning algorithm can monitor the situation of each task through a well designed learning situation indicator and adaptively assign the proper loss weights for different tasks according to their learning situation and the hierarchical structure, which can significantly improve the stability and the efficiency of the training process. Extensive experiments demonstrate the effectiveness of the proposed method.The overall model can infer more reliable depth and location information than existing methods, which achieves the state-of-the-art performance on the KITTI benchmark.
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders. By contrast, despite the natural symmetry, the design of effective algorithms for exploiting large-scale language pretraining remains under-explored. In this work, we are the first to investigate the design of such algorithms and propose a novel generalized distillation method,TeachText, which leverages complementary cues from multiple text encoders to provide an enhanced supervisory signal to the retrieval model. Moreover, we extend our method to video side modalities and show that we can effectively reduce the number of used modalities at test time without compromising performance. Our approach advances the state of the art on several video retrieval benchmarks by a significant margin and adds no computational overhead at test time. Last but not least, we show an effective application of our method for eliminating noise from retrieval datasets. Code and data can be found at https://www.robots.ox.ac.uk/ vgg/research/teachtext/.
Learning Anchored Unsigned Distance Functions With Gradient Direction Alignment for Single-View Garment Reconstruction
PDF ↗While single-view 3D reconstruction has made significant progress benefiting from deep shape representations in recent years, garment reconstruction is still not solved well due to open surfaces, diverse topologies and complex geometric details. In this paper, we propose a novel learnable Anchored Unsigned Distance Function (AnchorUDF) representation for 3D garment reconstruction from a single image. AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution. To capture diverse garment topologies, AnchorUDF not only computes pixel-aligned local image features of query points, but also leverages a set of anchor points located around the surface to enrich 3D position features for query points, which provides stronger 3D space context for the distance function. Furthermore, in order to obtain more accurate point projection direction at inference, we explicitly align the spatial gradient direction of AnchorUDF with the ground-truth direction to the surface during training. Extensive experiments on two public 3D garment datasets, i.e., MGN and Deep Fashion3D, demonstrate that AnchorUDF achieves the state-of-the-art performance on single-view garment reconstruction. Code is available at https://github.com/zhaofang0627/AnchorUDF.
The unsupervised domain adaptation (UDA) has been widely adopted to alleviate the data scalability issue, while the existing works usually focus on classifying independently discrete labels. However, in many tasks (e.g., medical diagnosis), the labels are discrete and successively distributed. The UDA for ordinal classification requires inducing non-trivial ordinal distribution prior to the latent space. Target for this, the partially ordered set (poset) is defined for constraining the latent vector. Instead of the typically i.i.d. Gaussian latent prior, in this work, a recursively conditional Gaussian (RCG) set is adapted for ordered constraint modeling, which admits a tractable joint distribution prior. Furthermore, we are able to control the density of content vector that violates the poset constraints by a simple "three-sigma rule". We explicitly disentangle the cross-domain images into a shared ordinal prior induced ordinal content space and two separate source/target ordinal-unrelated spaces, and the self-training is worked on the shared space exclusively for ordinal-aware domain alignment. Extensive experiments on UDA medical diagnoses and facial age estimation demonstrate its effectiveness.
Various deep learning techniques have been proposed to solve the single-view 2D-to-3D pose estimation problem. While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory. In this work, we target these hard poses and present a novel skeletal GNN learning solution. To be specific, we propose a hop-aware hierarchical channel-squeezing fusion layer to effectively extract relevant information from neighboring nodes while suppressing undesired noises in GNN learning. In addition, we propose a temporal-aware dynamic graph construction procedure that is robust and effective for 3D pose estimation. Experimental results on the Human3.6M dataset show that our solution achieves a 10.3% average prediction accuracy improvement and greatly improves on hard poses over state-of-the-art techniques. We further apply the proposed technique on the skeleton-based action recognition task and also achieve state-of-the-art performance.
Point cloud registration is a key task in many computational fields. Previous correspondence matching based methods require the inputs to have distinctive geometric structures to fit a 3D rigid transformation according to point-wise sparse feature matches. However, the accuracy of transformation heavily relies on the quality of extracted features, which are prone to errors with respect to partiality and noise. In addition, they can not utilize the geometric knowledge of all the overlapping regions. On the other hand, previous global feature based approaches can utilize the entire point cloud for the registration, however they ignore the negative effect of non-overlapping points when aggregating global features. In this paper, we present OMNet, a global feature based iterative network for partial-to-partial point cloud registration. We learn overlapping masks to reject non-overlapping regions, which converts the partial-to-partial registration to the registration of the same shape. Moreover, the previously used data is sampled only once from the CAD models for each object, resulting in the same point clouds for the source and reference. We propose a more practical manner of data generation where a CAD model is sampled twice for the source and reference, avoiding the previously prevalent over-fitting issue. Experimental results show that our method achieves state-of-the-art performance compared to traditional and deep learning based methods. Code is available at https://github.com/megvii-research/OMNet.
This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem. For data augmentation, most existing methods directly adopt the standard operations designed for single-modality visible images, and thus do not fully consider the imagery properties in visible to infrared matching. Our basic idea is to homogenously generate color-irrelevant images by randomly exchanging the color channels. It can be seamlessly integrated into existing augmentation operations without modifying the network, consistently improving the robustness against color variations. Incorporated with a random erasing strategy, it further greatly enriches the diversity by simulating random occlusions. For cross-modality metric learning, we design an enhanced channel-mixed learning strategy to simultaneously handle the intra- and cross-modality variations with squared difference for stronger discriminability. Besides, a channel-augmented joint learning strategy is further developed to explicitly optimize the outputs of augmented images. Extensive experiments with insightful analysis on two visible-infrared recognition tasks show that the proposed strategies consistently improve the accuracy. Without auxiliary information, it improves the state-of-the-art Rank-1/mAP by 14.59%/13.00% on the large-scale SYSU-MM01 dataset.
We propose a novel approach for embedding novel views in a single JPEG image while preserving the perceptual fidelity of the modified JPEG image and the restored novel views. We adopt the popular novel view synthesis representation of multiplane images (MPIs). Our model first encodes 32 MPI layers (totally 128 channels) into a 3-channel JPEG image that can be decoded for MPIs to render novel views, with an embedding capacity of 1024 bits per pixel. We conducted experiments on public datasets with different novel view synthesis methods, and the results show that the proposed method can restore high-fidelity novel views from a slightly modified JPEG image. Furthermore, our method is robust to JPEG compression, color adjusting, and cropping. Our source code will be publicly available.
Self-supervised monocular depth estimation has become an appealing solution to the lack of ground truth labels, but its reconstruction loss often produces over-smoothed results across object boundaries and is incapable of handling occlusion explicitly. In this paper, we propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods. The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps. To cope with the prediction error of the confidence map itself, we also leverage the threshold network that learns the threshold dynamically conditioned on the pseudo depth maps. The pseudo depth labels filtered out by the thresholded confidence map are used to supervise the monocular depth network. Furthermore, we propose the probabilistic framework that refines the monocular depth map with the help of its uncertainty map through the pixel-adaptive convolution (PAC) layer. Experimental results demonstrate superior performance to state-of-the-art monocular depth estimation methods. Lastly, we exhibit that the proposed threshold learning can also be used to improve the performance of existing confidence estimation approaches.
Consider a scenario where we are supplied with a number of ready-to-use models trained on a certain source domain and hope to directly apply the most appropriate ones to different target domains based on the models' relative performance. Ideally we should annotate a validation set for model performance assessment on each new target environment, but such annotations are often very expensive. Under this circumstance, we introduce the problem of ranking models in unlabeled new environments. For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates. We first select labeled datasets as the proxy. Specifically, datasets that are more similar to the unlabeled target domain are found to better preserve the relative performance rankings. Motivated by this, we further propose to search the proxy set by sampling images from various datasets that have similar distributions as the target. We analyze the problem and its solutions on the person re-identification (re-ID) task, for which sufficient datasets are publicly available, and show that a carefully constructed proxy set effectively captures relative performance ranking in new environments. Code is avalible at https://github.com/sxzrt/Proxy-Set.
Recognizing new objects by learning from a few labeled examples in an evolving environment is crucial to obtain excellent generalization ability for real-world machine learning systems. A typical setting across current meta learning algorithms assumes a stationary task distribution during meta training. In this paper, we explore a more practical and challenging setting where task distribution changes over time with domain shift. Particularly, we consider realistic scenarios where task distribution is highly imbalanced with domain labels unavailable in nature. We propose a kernel-based method for domain change detection and a difficulty-aware memory management mechanism that jointly considers the imbalanced domain size and domain importance to learn across domains continuously. Furthermore, we introduce an efficient adaptive task sampling method during meta training, which significantly reduces task gradient variance with theoretical guarantees. Finally, we propose a challenging benchmark with imbalanced domain sequences and varied domain difficulty. We have performed extensive evaluations on the proposed benchmark, demonstrating the effectiveness of our method.