CVPR 2022 论文列表

We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation. To leverage the unlabeled data to boost model performance, we present a novel Two-Way Inter-label Self-Training framework named TWIST. It exploits inherent correlations between semantic understanding and instance information of a scene. Specifically, we consider two kinds of pseudo labels for semantic- and instance-level supervision. Our key design is to provide object-level information for denoising pseudo labels and make use of their correlation for two-way mutual enhancement, thereby iteratively promoting the pseudo-label qualities. TWIST attains leading performance on both ScanNet and S3DIS, compared to recent 3D pre-training approaches, and can cooperate with them to further enhance performance, e.g., +4.4% AP50 on 1%-label ScanNet data-efficient benchmark. Code is available at https://github.com/dvlab-research/TWIST.

As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it inappropriate for layout-specific applications, e.g., face recognition and medical image segmentation. We observe that these applications naturally exhibit the characteristics of large intra-image (spatial) variance and small cross-image variance. This observation motivates our efficient translation variant convolution (TVConv) for layout-aware visual processing. Technically, TVConv is composed of affinity maps and a weight-generating block. While affinity maps depict pixel-paired relationships gracefully, the weight-generating block can be explicitly overparameterized for better training while maintaining efficient inference. Although conceptually simple, TVConv significantly improves the efficiency of the convolution and can be readily plugged into various network architectures. Extensive experiments on face recognition show that TVConv reduces the computational cost by up to 3.1x and improves the corresponding throughput by 2.3x while maintaining a high accuracy compared to the depthwise convolution. Moreover, for the same computation cost, we boost the mean accuracy by up to 4.21%. We also conduct experiments on the optic disc/cup segmentation task and obtain better generalization performance, which helps mitigate the critical data scarcity issue. Code is available at https://github.com/JierunChen/TVConv.

Continuous normalizing flows (CNFs) construct invertible mappings between an arbitrary complex distribution and an isotropic Gaussian distribution using Neural Ordinary Differential Equations (neural ODEs). It has not been tractable on large datasets due to the incremental complexity of the neural ODE training. Optimal Transport theory has been applied to regularize the dynamics of the ODE to speed up training in recent works. In this paper, a temporal optimization is proposed by optimizing the evolutionary time for forward propagation of the neural ODE training. In this appoach, we optimize the network weights of the CNF alternately with evolutionary time by coordinate descent. Further with temporal regularization, stability of the evolution is ensured. This approach can be used in conjunction with the original regularization approach. We have experimentally demonstrated that the proposed approach can significantly accelerate training without sacrifying performance over baseline models.

Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal contexts are incorporated at two levels: the extraction of features and the refinement of similarity maps. Specifically, for feature extraction, an online temporally adaptive convolution is proposed to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights according to the previous frames. For similarity map refinement, we propose an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map. TCTrack is effective and efficient: evaluation on four aerial tracking benchmarks shows its impressive performance; real-world UAV tests show its high speed of over 27 FPS on NVIDIA Jetson AGX Xavier.

Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement. Unfortunately, the datasets for rPPG are limited as they require videos of the human face paired with ground-truth, synchronized heart rate data from a medical-grade health monitor. Also troubling is that the datasets are not inclusive of diverse populations, i.e., current real rPPG facial video datasets are imbalanced in terms of races or skin tones, leading to accuracy disparities on different demographic groups. This paper proposes a scalable biophysical learning based method to generate physio-realistic synthetic rPPG videos given any reference image and target rPPG signal and shows that it could further improve the state-of-the-art physiological measurement and reduce the bias among different groups. We also collect the largest rPPG dataset of its kind (UCLA-rPPG) with a diverse presence of subject skin tones, in the hope that this could serve as a benchmark dataset for different skin tones in this area and ensure that advances of the technique can benefit all people for healthcare equity. The dataset is available at https://visual.ee.ucla.edu/rppg_avatars.htm/.

The Event-based Synthetic Aperture Imaging (E-SAI) has recently been proposed to see through extremely dense occlusions. However, the performance of E-SAI is not consistent under sparse occlusions due to the dramatic decrease of signal events. This paper addresses this problem by leveraging the merits of both events and frames, leading to a fusion-based SAI (EF-SAI) that performs consistently under the different densities of occlusions. In particular, we first extract the feature from events and frames via multi-modal feature encoders and then apply a multi-stage fusion network for cross-modal enhancement and density-aware feature selection. Finally, a CNN decoder is employed to generate occlusion-free visual images from selected features. Extensive experiments show that our method effectively tackles varying densities of occlusions and achieves superior performance to the state-of-the-art SAI methods. Codes and datasets are available at https://github.com/smjsc/EF-SAI

Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods adhere to the paradigm that the prediction is made "from one character to another", which inevitably yields prediction errors due to the complicated structures of mathematical expressions or crabbed handwritings. In this paper, we propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network. Specifically, we present a set of grammar rules for converting the LaTeX markup sequence of each expression into a parsing tree; then, we model the markup sequence prediction as a tree traverse process with a deep neural network. In this way, the proposed method can effectively describe the syntax context of expressions, alleviating the structure prediction errors of HMER. Experiments on three benchmark datasets demonstrate that our method achieves better recognition performance than prior arts. To further validate the effectiveness of our method, we create a large-scale dataset consisting of 100k handwritten mathematical expression images acquired from ten thousand writers. The source code, new dataset, and pre-trained models of this work will be publicly available.

Visual exploration is a task that seeks to visit all the navigable areas of an environment as quickly as possible. The existing methods employ deep reinforcement learning (RL) as the standard tool for the task. However, they tend to be vulnerable to statistical shifts between the training and test data, resulting in poor generalization over novel environments that are out-of-distribution (OOD) from the training data. In this paper, we attempt to improve the generalization ability by utilizing the inductive biases available for the task. Employing the active neural SLAM (ANS) that learns exploration policies with the advantage actor-critic (A2C) method as the base framework, we first point out that the mappings represented by the actor and the critic should satisfy specific symmetries. We then propose a network design for the actor and the critic to inherently attain these symmetries. Specifically, we use G-convolution instead of the standard convolution and insert the semi-global polar pooling (SGPP) layer, which we newly design in this study, in the last section of the critic network. Experimental results show that our method increases area coverage by 8.1 square meters when trained on the Gibson dataset and tested on the Matterport3D dataset, establishing the new state-of-the-art.

We propose a keypoint-based object-level SLAM framework that can provide globally consistent 6DoF pose estimates for symmetric and asymmetric objects alike. To the best of our knowledge, our system is among the first to utilize the camera pose information from SLAM to provide prior knowledge for tracking keypoints on symmetric objects - ensuring that new measurements are consistent with the current 3D scene. Moreover, our semantic keypoint network is trained to predict the Gaussian covariance for the keypoints that captures the true error of the prediction, and thus is not only useful as a weight for the residuals in the system's optimization problems, but also as a means to detect harmful statistical outliers without choosing a manual threshold. Experiments show that our method provides competitive performance to the state of the art in 6DoF object pose estimation, and at a real-time speed. Our code, pre-trained models, and keypoint labels are available https://github.com/rpng/suo_slam.

We study the challenging incremental few-shot object detection (iFSD) setting. Recently, hypernetwork-based approaches have been studied in the context of continuous and finetune-free iFSD with limited success. We take a closer look at important design choices of such methods, leading to several key improvements and resulting in a more accurate and flexible framework, which we call Sylph. In particular, we demonstrate the effectiveness of decoupling object classification from localization by leveraging a base detector that is pretrained for class-agnostic localization on large-scale dataset. Contrary to what previous results have suggested, we show that with a carefully designed class-conditional hypernetwork, finetune-free iFSD can be highly effective, especially when a large number of base categories with abundant data are available for meta-training, almost approaching alternatives that undergo test-time-training. This result is even more significant considering its many practical advantages: (1) incrementally learning new classes in sequence without additional training, (2) detecting both novel and seen classes in a single pass, and (3) no forgetting of previously seen classes. We benchmark our model on both COCO and LVIS, reporting as high as 17% AP on the long-tail rare classes on LVIS, indicating the promise of hypernetwork-based iFSD.

End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Conversion mechanism to explicitly guide text localization through recognition loss. The straightforward design results in a concise framework that requires neither additional rectification module nor character-level annotation for the arbitrarily-shaped text. Qualitative and quantitative experiments on multi-oriented datasets RoIC13 and ICDAR 2015, arbitrarily-shaped datasets Total-Text and CTW1500, and multi-lingual datasets ReCTS (Chinese) and VinText (Vietnamese) demonstrate SwinTextSpotter significantly outperforms existing methods. Code is available at https://github.com/mxin262/SwinTextSpotter.

The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video transformer to encode spatial-temporal representations that can adapt to variable lengths of video input without dedicated design for different frame rates. Based on this model architecture, we show that video captioning can benefit significantly from more densely sampled video frames as opposed to previous successes with sparsely sampled video frames for video-and-language understanding tasks (e.g., video question answering). Moreover, to avoid the inherent redundancy in consecutive video frames, we propose adaptively learning a sparse attention mask and optimizing it for task-specific performance improvement through better long-range video sequence modeling. Through extensive experiments on 5 video captioning datasets, we show that SwinBERT achieves across-the-board performance improvements over previous methods, often by a large margin. The learned sparse attention masks in addition push the limit to new state of the arts, and can be transferred between different video lengths and between different datasets. Code is available at https://github.com/microsoft/SwinBERT

We present techniques for scaling Swin Transformer [??] up to 3 billion parameters and making it capable of training with images of up to 1,536x1,536 resolution. By scaling up capacity and resolution, Swin Transformer sets new records on four representative vision benchmarks: 84.0% top-1 accuracy on ImageNet-V2 image classification, 63.1 / 54.4 box / mask mAP on COCO object detection, 59.9 mIoU on ADE20K semantic segmentation, and 86.8% top-1 accuracy on Kinetics-400 video action classification. We tackle issues of training instability, and study how to effectively transfer models pre-trained at low resolutions to higher resolution ones. To this aim, several novel technologies are proposed: 1) a residual post normalization technique and a scaled cosine attention approach to improve the stability of large vision models; 2) a log-spaced continuous position bias technique to effectively transfer models pre-trained at low-resolution images and windows to their higher-resolution counterparts. In addition, we share our crucial implementation details that lead to significant savings of GPU memory consumption and thus make it feasible to train large vision models with regular GPUs. Using these techniques and self-supervised pre-training, we successfully train a strong 3 billion Swin Transformer model and effectively transfer it to various vision tasks involving high-resolution images or windows, achieving the state-of-the-art accuracy on a variety of benchmarks. Code is available at https://github.com/microsoft/Swin-Transformer.

While Visual Question Answering (VQA) has progressed rapidly, previous works raise concerns about robustness of current VQA models. In this work, we study the robustness of VQA models from a novel perspective: visual context. We suggest that the models over-rely on the visual context, i.e., irrelevant objects in the image, to make predictions. To diagnose the models' reliance on visual context and measure their robustness, we propose a simple yet effective perturbation technique, SwapMix. SwapMix perturbs the visual context by swapping features of irrelevant context objects with features from other objects in the dataset. Using SwapMix we are able to change answers to more than 45% of the questions for a representative VQA model. Additionally, we train the models with perfect sight and find that the context over-reliance highly depends on the quality of visual representations. In addition to diagnosing, SwapMix can also be applied as a data augmentation strategy during training in order to regularize the context over-reliance. By swapping the context object features, the model reliance on context can be suppressed effectively. Two representative VQA models are studied using SwapMix: a co-attention model MCAN and a large-scale pretrained model LXMERT. Our experiments on the popular GQA dataset show the effectiveness of SwapMix for both diagnosing model robustness, and regularizing the over-reliance on visual context.

We explore the potential of CNN-based models for gallbladder cancer (GBC) detection from ultrasound (USG) images as no prior study is known. USG is the most common diagnostic modality for GB diseases due to its low cost and accessibility. However, USG images are challenging to analyze due to low image quality, noise, and varying viewpoints due to the handheld nature of the sensor. Our exhaustive study of state-of-the-art (SOTA) image classification techniques for the problem reveals that they often fail to learn the salient GB region due to the presence of shadows in the USG images. SOTA object detection techniques also achieve low accuracy because of spurious textures due to noise or adjacent organs. We propose GBCNet to tackle the challenges in our problem. GBCNet first extracts the regions of interest (ROIs) by detecting the GB (and not the cancer), and then uses a new multi-scale, second-order pooling architecture specializing in classifying GBC. To effectively handle spurious textures, we propose a curriculum inspired by human visual acuity, which reduces the texture biases in GBCNet. Experimental results demonstrate that GBCNet significantly outperforms SOTA CNN models, as well as the expert radiologists. Our technical innovations are generic to other USG image analysis tasks as well. Hence, as a validation, we also show the efficacy of GBCNet in detecting breast cancer from USG images. Project page with source code, trained models, and data is available at https://gbc-iitd.github.io/gbcnet.

We propose a new method for reconstructing controllable implicit 3D human models from sparse multi-view RGB videos. Our method defines the neural scene representation on the mesh surface points and signed distances from the surface of a human body mesh. We identify an indistinguishability issue that arises when a point in 3D space is mapped to its nearest surface point on a mesh for learning surface-aligned neural scene representation. To address this issue, we propose projecting a point onto a mesh surface using a barycentric interpolation with modified vertex normals. Experiments with the ZJU-MoCap and Human3.6M datasets show that our approach achieves a higher quality in a novel-view and novel-pose synthesis than existing methods. We also demonstrate that our method easily supports the control of body shape and clothes. Project page: https://pfnet-research.github.io/surface-aligned-nerf/.

Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs) with some parameters encoding the local contexts. To reconstruct a surface at a specific query location at inference time, these methods then match the local reconstruction target by searching for the best match in the local prior space (by optimizing the parameters encoding the local context) at the given query location. However, this requires the local context prior to generalize to a wide variety of unseen target regions, which is hard to achieve. To resolve this issue, we introduce Predictive Context Priors by learning Predictive Queries for each specific point cloud at inference time. Specifically, we first train a local context prior using a large point cloud dataset similar to previous techniques. For surface reconstruction at inference time, however, we specialize the local context prior into our Predictive Context Prior by learning Predictive Queries, which predict adjusted spatial query locations as displacements of the original locations. This leads to a global SDF that fits the specific point cloud the best. Intuitively, the query prediction enables us to flexibly search the learned local context prior over the entire prior space, rather than being restricted to the fixed query locations, and this improves the generalizability. Our method does not require ground truth signed distances, normals, or any additional procedure of signed distance fusion across overlapping regions. Our experimental results in surface reconstruction for single shapes or complex scenes show significant improvements over the state-of-the-art under widely used benchmarks. Code and data are available at https://github.com/mabaorui/PredictableContextPrior.

We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at surfemb.github.io.

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques on top of trivially pooled visual features. Instead, in this paper, we focus on the unique challenges encountered in lip reading and propose tailored solutions. To this end, we make the following contributions: (1) we propose an attention-based pooling mechanism to aggregate visual speech representations; (2) we use sub-word units for lip reading for the first time and show that this allows us to better model the ambiguities of the task; (3) we propose a model for Visual Speech Detection (VSD), trained on top of the lip reading network. Following the above, we obtain state-of-the-art results on the challenging LRS2 and LRS3 benchmarks when training on public datasets, and even surpass models trained on large-scale industrial datasets by using an order of magnitude less data. Our best model achieves 22.6% word error rate on the LRS2 dataset, a performance unprecedented for lip reading models, significantly reducing the performance gap between lip reading and automatic speech recognition. Moreover, on the AVA-ActiveSpeaker benchmark, our VSD model surpasses all visual-only baselines and even outperforms several recent audio-visual methods.