CVPR 2022 论文列表

Computer vision systems today are primarily N-purpose systems, designed and trained for a predefined set of tasks. Adapting such systems to new tasks is challenging and often requires non-trivial modifications to the network architecture (e.g. adding new output heads) or training process (e.g. adding new losses). To reduce the time and expertise required to develop new applications, we would like to create general purpose vision systems that can learn and perform a range of tasks without any modification to the architecture or learning process. In this paper, we propose GPV-1, a task-agnostic vision-language architecture that can learn and perform tasks that involve receiving an image and producing text and/or bounding boxes, including classification, localization, visual question answering, captioning, and more. We also propose evaluations of generality of architecture, skill-concept transfer, and learning efficiency that may inform future work on general purpose vision. Our experiments indicate GPV-1 is effective at multiple tasks, reuses some concept knowledge across tasks, can perform the Referring Expressions task zero-shot, and further improves upon the zero-shot performance using a few training samples.

Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performance. Our algorithm, Region Impurity and Prediction Uncertainty (RIPU), introduces a new acquisition strategy characterizing the spatial adjacency of image regions along with the prediction confidence. We show that the proposed region-based selection strategy makes more efficient use of a limited budget than image-based or point-based counterparts. Further, we enforce local prediction consistency between a pixel and its nearest neighbors on a source image. Alongside, we develop a negative learning loss to make the features more discriminative. Extensive experiments demonstrate that our method only requires very few annotations to almost reach the supervised performance and substantially outperforms state-of-the-art methods. The code is available at https://github.com/BIT-DA/RIPU.

Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The first hierarchical scene text dataset is introduced to enable this novel research task. We also propose a novel method that is able to simultaneously detect scene text and form text clusters in a unified way. Comprehensive experiments show that our unified model achieves better performance than multiple well-designed baseline methods. Additionally, this model achieves state-of-the-art results on multiple scene text detection datasets without the need of complex post-processing. Dataset and code: https://github.com/google-research-datasets/hiertext.

Recently, Sharpness-Aware Minimization (SAM), which connects the geometry of the loss landscape and generalization, has demonstrated a significant performance boost on training large-scale models such as vision transformers. However, the update rule of SAM requires two sequential (non-parallelizable) gradient computations at each step, which can double the computational overhead. In this paper, we propose a novel algorithm LookSAM - that only periodically calculates the inner gradient ascent, to significantly reduce the additional training cost of SAM. The empirical results illustrate that LookSAM achieves similar accuracy gains to SAM while being tremendously faster - it enjoys comparable computational complexity with first-order optimizers such as SGD or Adam. To further evaluate the performance and scalability of LookSAM, we incorporate a layer-wise modification and perform experiments in the large-batch training scenario, which is more prone to converge to sharp local minima. Equipped with the proposed algorithms, we are the first to successfully scale up the batch size when training Vision Transformers (ViTs). With a 64k batch size, we are able to train ViTs from scratch in minutes while maintaining competitive performance. The code is available here: https://github.com/yong-6/LookSAM

After the 2017 TuSimple Lane Detection Challenge, its dataset and evaluation based on accuracy and F1 score have become the de facto standard to measure the performance of lane detection methods. While they have played a major role in improving the performance of lane detection methods, the validity of this evaluation method in downstream tasks has not been adequately researched. In this study, we design 2 new driving-oriented metrics for lane detection: End-to-End Lateral Deviation metric (E2E-LD) is directly formulated based on the requirements of autonomous driving, a core task downstream of lane detection; Per-frame Simulated Lateral Deviation metric (PSLD) is a lightweight surrogate metric of E2E-LD. To evaluate the validity of the metrics, we conduct a large-scale empirical study with 4 major types of lane detection approaches on the TuSimple dataset and our newly constructed dataset Comma2k19-LD. Our results show that the conventional metrics have strongly negative correlations (<=-0.55) with E2E-LD, meaning that some recent improvements purely targeting the conventional metrics may not have led to meaningful improvements in autonomous driving, but rather may actually have made it worse by overfitting to the conventional metrics. On the contrary, PSLD shows statistically significant strong positive correlations (>=0.38) with E2E-LD. As a result, the conventional metrics tend to overestimate less robust models. As autonomous driving is a security/safety-critical system, the underestimation of robustness hinders the sound development of practical lane detection models. We hope that our study will help the community achieve more downstream task-aware evaluations for lane detection.

The ability to synthesize long-term human motion sequences in real-world scenes can facilitate numerous applications. Previous approaches for scene-aware motion synthesis are constrained by pre-defined target objects or positions and thus limit the diversity of human-scene interactions for synthesized motions. In this paper, we focus on the problem of synthesizing diverse scene-aware human motions under the guidance of target action sequences. To achieve this, we first decompose the diversity of scene aware human motions into three aspects, namely interaction diversity (e.g. sitting on different objects with different poses in the given scenes), path diversity (e.g. moving to the target locations following different paths), and the motion diversity (e.g. having various body movements during moving). Based on this factorized scheme, a hierarchical framework is proposed with each sub-module responsible for modeling one aspect. We assess the effectiveness of our framework on two challenging datasets for scene-aware human motion synthesis. The experiment results show that the proposed framework remarkably outperforms the previous methods in terms of diversity and naturalness.

Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation of targets. Although this strategy is effective, it fails to fully exploit the information contained in a whole trajectory. To this end, we propose a strategy, namely multi-view trajectory contrastive learning, in which each trajectory is represented as a center vector. By maintaining all the vectors in a dynamically updated memory bank, a trajectory-level contrastive loss is devised to explore the inter-frame information in the whole trajectories. Besides, in this strategy, each target is represented as multiple adaptively selected keypoints rather than a pre-defined anchor or center. This design allows the network to generate richer representation from multiple views of the same target, which can better characterize occluded objects. Additionally, in the inference stage, a similarity-guided feature fusion strategy is developed for further boosting the quality of the trajectory representation. Extensive experiments have been conducted on MOTChallenge to verify the effectiveness of the proposed techniques. The experimental results indicate that our method has surpassed preceding trackers and established new state-of-the-art performance.

Semi-supervised learning (SSL) has been studied for a long time to solve vision tasks in data-efficient application scenarios. SSL aims to learn a good classification model using a few labeled data together with large-scale unlabeled data. Recent advances achieve the goal by combining multiple SSL techniques, e.g., self-training and consistency regularization. From unlabeled samples, they usually adopt a confidence filter (CF) to select reliable ones with high prediction confidence. In this work, we study whether the moderately confident samples are useless and how to select the useful ones to improve model optimization. To answer these problems, we propose a novel Taylor expansion inspired filtration (TEIF) framework, which admits the samples of moderate confidence with similar feature or gradient to the respective one averaged over the labeled and highly confident unlabeled data. It can produce a stable and new information induced network update, leading to better generalization. Two novel filters are derived from this framework and can be naturally explained in two perspectives. One is gradient synchronization filter (GSF), which strengthens the optimization dynamic of fully-supervised learning; it selects the samples whose gradients are similar to class-wise majority gradients. The other is prototype proximity filter (PPF), which involves more prototypical samples in training to learn better semantic representations; it selects the samples near class-wise prototypes. They can be integrated into SSL methods with CF. We use the state-of-the-art FixMatch as the baseline. Experiments on popular SSL benchmarks show that we achieve the new state of the art.

Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect clone-model performance using softmax predictions of the classification network, most of the APIs allow access to only the top-1 labels. In this work, we show that it is indeed possible to steal Machine Learning models by accessing only top-1 predictions (Hard Label setting) as well, without access to model gradients (Black-Box setting) or even the training dataset (Data-Free setting) within a low query budget. We propose a novel GAN-based framework that trains the student and generator in tandem to steal the model effectively while overcoming the challenge of the hard label setting by utilizing gradients of the clone network as a proxy to the victim's gradients. We propose to overcome the large query costs associated with a typical Data-Free setting by utilizing publicly available (potentially unrelated) datasets as a weak image prior. We additionally show that even in the absence of such data, it is possible to achieve state-of-the-art results within a low query budget using synthetically crafted samples. We are the first to demonstrate the scalability of Model Stealing in a restricted access setting on a 100 class dataset as well.

Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world applicability of such models, there are growing interests to develop models optimized for arbitrary upscaling factors. Our proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process. Using joint optimization of both directions, the proposed model is able to learn upscaling and downscaling simultaneously and achieve bidirectional arbitrary image rescaling. It improves the performance of current arbitrary upscaling models by a large margin while at the same time learns to maintain visual perception quality in downscaled images. The proposed model is further shown to be robust in cycle idempotence test, free of severe degradations in reconstruction accuracy when the downscaling-to-upscaling cycle is applied repetitively. This robustness is beneficial for image rescaling in the wild when this cycle could be applied to one image for multiple times. It also performs well on tests with arbitrary large scales and asymmetric scales, even when the model is not trained with such tasks. Extensive experiments are conducted to demonstrate the superior performance of our model.

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the models' decisions. Evaluating such methods is challenging since no ground truth attributions exist. We thus propose three novel evaluation schemes to more reliably measure the faithfulness of those methods, to make comparisons between them more fair, and to make visual inspection more systematic. To address faithfulness, we propose a novel evaluation setting (DiFull) in which we carefully control which parts of the input can influence the output in order to distinguish possible from impossible attributions. To address fairness, we note that different methods are applied at different layers, which skews any comparison, and so evaluate all methods on the same layers (ML-Att) and discuss how this impacts their performance on quantitative metrics. For more systematic visualizations, we propose a scheme (AggAtt) to qualitatively evaluate the methods on complete datasets. We use these evaluation schemes to study strengths and shortcomings of some widely used attribution methods. Finally, we propose a post-processing smoothing step that significantly improves the performance of some attribution methods, and discuss its applicability.

Plasticity-stability dilemma is a main problem for incremental learning, where plasticity is referring to the ability to learn new knowledge, and stability retains the knowledge of previous tasks. Many methods tackle this problem by storing previous samples, while in some applications, training data from previous tasks cannot be legally stored. In this work, we propose to employ mode connectivity in loss landscapes to achieve better plasticity-stability trade-off without any previous samples. We give an analysis of why and how to connect two independently optimized optima of networks, null-space projection for previous tasks and simple SGD for the current task, can attain a meaningful balance between preserving already learned knowledge and granting sufficient flexibility for learning a new task. This analysis of mode connectivity also provides us a new perspective and technology to control the trade-off between plasticity and stability. We evaluate the proposed method on several benchmark datasets. The results indicate our simple method can achieve notable improvement, and perform well on both the past and current tasks. On 10-split-CIFAR-100 task, our method achieves 79.79% accuracy, which is 6.02% higher. Our method also achieves 6.33% higher accuracy on TinyImageNet. Code is available at https://github.com/lingl1024/Connector.

Accurate facial landmarks are essential prerequisites for many tasks related to human faces. In this paper, an accurate facial landmark detector is proposed based on cascaded transformers. We formulate facial landmark detection as a coordinate regression task such that the model can be trained end-to-end. With self-attention in transformers, our model can inherently exploit the structured relationships between landmarks, which would benefit landmark detection under challenging conditions such as large pose and occlusion. During cascaded refinement, our model is able to extract the most relevant image features around the target landmark for coordinate prediction, based on deformable attention mechanism, thus bringing more accurate alignment. In addition, we propose a novel decoder that refines image features and landmark positions simultaneously. With few parameter increasing, the detection performance improves further. Our model achieves new state-of- the-art performance on several standard facial landmark detection benchmarks, and shows good generalization ability in cross-dataset evaluation.

The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estimator that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we collect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects.

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. To be specific, we establish a cascaded illumination learning process with weight sharing to handle this task. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage, producing the gains that only use the single basic block for inference (yet has not been exploited in previous works), which drastically diminishes computation cost. We then define the unsupervised training loss to elevate the model capability that can adapt general scenes. Further, we make comprehensive explorations to excavate SCI's inherent properties (lacking in existing works) including operation-insensitive adaptability (acquiring stable performance under the settings of different simple operations) and model-irrelevant generality (can be applied to illumination-based existing works to improve performance). Finally, plenty of experiments and ablation studies fully indicate our superiority in both quality and efficiency. Applications on low-light face detection and nighttime semantic segmentation fully reveal the latent practical values for SCI. The source code is available at https://github.com/vis-opt-group/SCI.

Optimization within a layer of a deep-net has emerged as a new direction for deep-net layer design. However, there are two main challenges when applying these layers to computer vision tasks: (a) which optimization problem within a layer is useful?; (b) how to ensure that computation within a layer remains efficient? To study question (a), in this work, we propose total variation (TV) minimization as a layer for computer vision. Motivated by the success of total variation in image processing, we hypothesize that TV as a layer provides useful inductive bias for deep-nets too. We study this hypothesis on five computer vision tasks: image classification, weakly-supervised object localization, edge-preserving smoothing, edge detection, and image denoising, improving over existing baselines. To achieve these results, we had to address question (b): we developed a GPU-based projected-Newton method which is 37x faster than existing solutions.

Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets. Recently DIFs-based methods have been proposed to handle shape reconstruction and dense point correspondences simultaneously, capturing semantic relationships across shapes of the same class by learning a DIFs-modeled shape template. These methods provide great flexibility and accuracy in reconstructing 3D shapes and inferring correspondences. However, the point correspondences built from these methods do not intrinsically preserve the topology of the shapes, unlike mesh-based template matching methods. This limits their applications on 3D geometries where underlying topological structures exist and matter, such as anatomical structures in medical images. In this paper, we propose a new model called Neural Diffeomorphic Flow (NDF) to learn deep implicit shape templates, representing shapes as conditional diffeomorphic deformations of templates, intrinsically preserving shape topologies. The diffeomorphic deformation is realized by an auto-decoder consisting of Neural Ordinary Differential Equation (NODE) blocks that progressively map shapes to implicit templates. We conduct extensive experiments on several medical image organ segmentation datasets to evaluate the effectiveness of NDF on reconstructing and aligning shapes. NDF achieves consistently state-of-the-art organ shape reconstruction and registration results in both accuracy and quality. The source code is publicly available at https://github.com/Siwensun/Neural_Diffeomorphic_Flow--NDF.

Knowledge of the road network topology is crucial for autonomous planning and navigation. Yet, recovering such topology from a single image has only been explored in part. Furthermore, it needs to refer to the ground plane, where also the driving actions are taken. This paper aims at extracting the local road network topology, directly in the bird's-eye-view (BEV), all in a complex urban setting. The only input consists of a single onboard, forward looking camera image. We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points. To better capture topology, we introduce the concept of minimal cycles and their covers. A minimal cycle is the smallest cycle formed by the directed curve segments (between two intersections). The cover is a set of curves whose segments are involved in forming a minimal cycle. We first show that the covers suffice to uniquely represent the road topology. The covers are then used to supervise deep neural networks, along with the lane curve supervision. These learn to predict the road topology from a single input image. The results on the NuScenes and Argoverse benchmarks are significantly better than those obtained with baselines. Code: https://github.com/ybarancan/TopologicalLaneGraph.