CVPR 2022 论文列表

General object detectors are always evaluated on hand-designed datasets, e.g., MS COCO and Pascal VOC, which tend to maintain balanced data distribution over different classes. However, it goes against the practical applications in the real world which suffer from a heavy class imbalance problem, known as the long-tailed object detection. In this paper, we propose a novel method, named Adaptive Hierarchical Representation Learning (AHRL), from a metric learning perspective to address long-tailed object detection. We visualize each learned class representation in the feature space, and observe that some classes, especially under-represented scarce classes, are prone to cluster with analogous ones due to the lack of discriminative representation. Inspired by this, we propose to split the whole feature space into a hierarchical structure and eliminate the problem in a divide-and-conquer way. AHRL contains a two-stage training paradigm. First, we train a normal baseline model and construct the hierarchical structure under the unsupervised clustering method. Then, we design an AHR loss that consists of two optimization objectives. On the one hand, AHR loss retains the hierarchical structure and keeps representation clusters away from each other. On the other hand, AHR loss adopts adaptive margins according to specific class pairs in the same cluster to further optimize locally. We conduct extensive experiments on the challenging LVIS dataset and AHRL outperforms all the existing state-of-the-art(SOTA) methods, with 29.1% segmentation AP and 29.3% box AP on LVIS v0.5 and 27.6% segmentation AP and 28.7% box AP on LVIS v1.0 based on ResNet-101. We hope our simple yet effective approach will serve as a solid baseline to help stimulate future research in long-tailed object detection. Code will be released soon.

Single-photon avalanche diodes (SPADs) are growing in popularity for depth sensing tasks. However, SPADs still struggle in the presence of high ambient light due to the effects of pile-up. Conventional techniques leverage fixed or asynchronous gating to minimize pile-up effects, but these gating schemes are all non-adaptive, as they are unable to incorporate factors such as scene priors and previous photon detections into their gating strategy. We propose an adaptive gating scheme built upon Thompson sampling. Adaptive gating periodically updates the gate position based on prior photon observations in order to minimize depth errors. Our experiments show that our gating strategy results in significantly reduced depth reconstruction error and acquisition time, even when operating outdoors under strong sunlight conditions.

Deep learning in the presence of noisy annotations has been studied extensively in classification, but much less in segmentation tasks. In this work, we study the learning dynamics of deep segmentation networks trained on inaccurately-annotated data. We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations. However, in contrast to classification, memorization in segmentation does not arise simultaneously for all semantic categories. Inspired by these findings, we propose a new method for segmentation from noisy annotations with two key elements. First, we detect the beginning of the memorization phase separately for each category during training. This allows us to adaptively correct the noisy annotations in order to exploit early learning. Second, we incorporate a regularization term that enforces consistency across scales to boost robustness against annotation noise. Our method outperforms standard approaches on a medical-imaging segmentation task where noises are synthesized to mimic human annotation errors. It also provides robustness to realistic noisy annotations present in weakly-supervised semantic segmentation, achieving state-of-the-art results on PASCAL VOC 2012. Code is available at https://github.com/Kangningthu/ADELE

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this problem by improving the diversity of the training data. We argue that diversity alone is not sufficient and that the characteristics of the training data need to be adapted to those of the new dataset such as camera viewpoint, position, human actions, and body size. To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator. AdaptPose follows an adversarial training scheme. From a source 3D pose the generator generates a sequence of 3D poses and a camera orientation that is used to project the generated poses to a novel view. Without any 3D labels or camera information AdaptPose successfully learns to create synthetic 3D poses from the target dataset while only being trained on 2D poses. In experiments on the Human3.6M, MPI-INF-3DHP, 3DPW, and Ski-Pose datasets our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.

Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of vision tasks recently. While achieving excellent performance, they still require relatively intensive computational cost that scales up drastically as the numbers of patches, self-attention heads and transformer blocks increase. In this paper, we argue that due to the large variations among images, their need for modeling long-range dependencies between patches differ. To this end, we introduce AdaViT, an adaptive computation framework that learns to derive usage policies on which patches, self-attention heads and transformer blocks to use throughout the backbone on a per-input basis, aiming to improve inference efficiency of vision transformers with a minimal drop of accuracy for image recognition. Optimized jointly with a transformer backbone in an end-to-end manner, a light-weight decision network is attached to the backbone to produce decisions on-the-fly. Extensive experiments on ImageNet demonstrate that our method obtains more than 2x improvement on efficiency compared to state-of-the-art vision transformers with only 0.8% drop of accuracy, achieving good efficiency/accuracy trade-offs conditioned on different computational budgets. We further conduct quantitative and qualitative analysis on learned usage polices and provide more insights on the redundancy in vision transformers.

We propose a new algorithm for training deep neural networks (DNNs) with binary weights. In particular, we first cast the problem of training binary neural networks (BiNNs) as a bilevel optimization instance and subsequently construct flexible relaxations of this bilevel program. The resulting training method shares its algorithmic simplicity with several existing approaches to train BiNNs, in particular with the straight-through gradient estimator successfully employed in BinaryConnect and subsequent methods. In fact, our proposed method can be interpreted as an adaptive variant of the original straight-through estimator that conditionally (but not always) acts like a linear mapping in the backward pass of error propagation. Experimental results demonstrate that our new algorithm offers favorable performance compared to existing approaches.

Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding image features with a set of learnable queries. However, this paradigm still suffers from slow convergence, limited performance, and design complexity of extra networks between backbone and decoder. In this paper, we find that the key to these issues is the adaptability of decoders for casting queries to varying objects. Accordingly, we propose a fast-converging query-based detector, named AdaMixer, by improving the adaptability of query-based decoding processes in two aspects. First, each query adaptively samples features over space and scales based on estimated offsets, which allows AdaMixer to efficiently attend to the coherent regions of objects. Then, we dynamically decode these sampled features with an adaptive MLP-Mixer under the guidance of each query. Thanks to these two critical designs, AdaMixer enjoys architectural simplicity without requiring dense attentional encoders or explicit pyramid networks. On the challenging MS COCO benchmark, AdaMixer with ResNet-50 as the backbone, with 12 training epochs, reaches up to 45.0 AP on the validation set along with 27.9 APs in detecting small objects. With the longer training scheme, AdaMixer with ResNeXt-101-DCN and Swin-S reaches 49.5 and 51.3 AP. Our work sheds light on a simple, accurate, and fast converging architecture for query-based object detectors. The code is made available at https://github.com/MCG-NJU/AdaMixer.

The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy. They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform. Focusing on this problem, we present AdaInt (Adaptive Intervals Learning), a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. In this way, a 3D LUT can increase its capability by conducting dense sampling in color ranges requiring highly non-linear transforms and sparse sampling for near-linear transforms. The proposed AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method. To enable the end-to-end learning of AdaInt, we design a novel differentiable operator called AiLUT-Transform (Adaptive Interval LUT Transform) to locate input colors in the non-uniform 3D LUT and provide gradients to the sampling intervals. Experiments demonstrate that methods equipped with AdaInt can achieve state-of-the-art performance on two public benchmark datasets with a negligible overhead increase. Our source code is available at https://github.com/ImCharlesY/AdaInt.

Recent works have shown that the computational efficiency of video recognition can be significantly improved by reducing the spatial redundancy. As a representative work, the adaptive focus method (AdaFocus) has achieved a favorable trade-off between accuracy and inference speed by dynamically identifying and attending to the informative regions in each video frame. However, AdaFocus requires a complicated three-stage training pipeline (involving reinforcement learning), leading to slow convergence and is unfriendly to practitioners. This work reformulates the training of AdaFocus as a simple one-stage algorithm by introducing a differentiable interpolation-based patch selection operation, enabling efficient end-to-end optimization. We further present an improved training scheme to address the issues introduced by the one-stage formulation, including the lack of supervision, input diversity and training stability. Moreover, a conditional-exit technique is proposed to perform temporal adaptive computation on top of AdaFocus without additional training. Extensive experiments on six benchmark datasets (i.e., ActivityNet, FCVID, Mini-Kinetics, Something-Something V1&V2, and Jester) demonstrate that our model significantly outperforms the original AdaFocus and other competitive baselines, while being considerably more simple and efficient to train. Code is available at https://github.com/ LeapLabTHU/AdaFocusV2.

Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in Supp.

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.

In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher for semi-supervised object detection (SSOD). Active Teacher extends the teacher-student framework to an iterative version, where the label set is partially initialized and gradually augmented by evaluating three key factors of unlabeled examples, including difficulty, information and diversity. With this design, Active Teacher can maximize the effect of limited label information while improving the quality of pseudo-labels. To validate our approach, we conduct extensive experiments on the MS-COCO benchmark and compare Active Teacher with a set of recently proposed SSOD methods. The experimental results not only validate the superior performance gain of Active Teacher over the compared methods, but also show that it enables the baseline network, ie, Faster-RCNN, to achieve 100% supervised performance with much less label expenditure, ie 40% labeled examples on MS-COCO. More importantly, we believe that the experimental analyses in this paper can provide useful empirical knowledge for data annotation in practical applications.

Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount of examples from unknown classes, resulting in the failure of most active learning methods. To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation. The LfOSA framework introduces an auxiliary network to model the per-example max activation value (MAV) distribution with a Gaussian Mixture Model, which can dynamically select the examples with highest probability from known classes in the unlabeled set. Moreover, by reducing the temperature T of the loss function, the detection model will be further optimized by exploiting both known and unknown supervision. The experimental results show that the proposed method can significantly improve the selection quality of known classes, and achieve higher classification accuracy with lower annotation cost than state-of-the-art active learning methods. To the best of our knowledge, this is the first work of active learning for open-set annotation.

The promise of active learning (AL) is to reduce labelling costs by selecting the most valuable examples to annotate from a pool of unlabelled data. Identifying these examples is especially challenging with high-dimensional data (e. g. images, videos) and in low-data regimes. In this paper, we propose a novel method for batch AL called ALFA-Mix. We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations. We construct interpolations between representations of labelled and unlabelled instances then examine the predicted labels. We show that inconsistencies in these predictions help discovering features that the model is unable to recognise in the unlabelled instances. We derive an efficient implementation based on a closed-form solution to the optimal interpolation causing changes in predictions. Our method outperforms all recent AL approaches in 30 different settings on 12 benchmarks of images, videos, and non-visual data. The improvements are especially significant in low-data regimes and on self-trained vision transformers, where ALFA-Mix outperforms the state-of-the-art in 59% and 43% of the experiments respectively.

We propose a method for compressively acquiring a dynamic light field (a 5-D volume) through a single-shot coded image (a 2-D measurement). We designed an imaging model that synchronously applies aperture coding and pixel-wise exposure coding within a single exposure time. This coding scheme enables us to effectively embed the original information into a single observed image. The observed image is then fed to a convolutional neural network (CNN) for light-field reconstruction, which is jointly trained with the camera-side coding patterns. We also developed a hardware prototype to capture a real 3-D scene moving over time. We succeeded in acquiring a dynamic light field with 5x5 viewpoints over 4 temporal sub-frames (100 views in total) from a single observed image. Repeating capture and reconstruction processes over time, we can acquire a dynamic light field at 4x the frame rate of the camera. To our knowledge, our method is the first to achieve a finer temporal resolution than the camera itself in compressive light-field acquisition. Our software is available from our project webpage.

While methods that regress 3D human meshes from images have progressed rapidly, the estimated body shapes often do not capture the true human shape. This is problematic since, for many applications, accurate body shape is as important as pose. The key reason that body shape accuracy lags pose accuracy is the lack of data. While humans can label 2D joints, and these constrain 3D pose, it is not so easy to "label" 3D body shape. Since paired data with images and 3D body shape are rare, we exploit two sources of information: (1) we collect internet images of diverse "fashion" models together with a small set of anthropometric measurements; (2) we collect linguistic shape attributes for a wide range of 3D body meshes and the model images. Taken together, these datasets provide sufficient constraints to infer dense 3D shape. We exploit the anthropometric measurements and linguistic shape attributes in several novel ways to train a neural network, called SHAPY, that regresses 3D human pose and shape from an RGB image. We evaluate SHAPY on public benchmarks, but note that they either lack significant body shape variation, ground-truth shape, or clothing variation. Thus, we collect a new dataset for evaluating 3D human shape estimation, called HBW, containing photos of "Human Bodies in the Wild" for which we have ground-truth 3D body scans. On this new benchmark, SHAPY significantly outperforms state-of-the-art methods on the task of 3D body shape estimation. This is the first demonstration that 3D body shape regression from images can be trained from easy-to-obtain anthropometric measurements and linguistic shape attributes. Our model and data are available at: shapy.is.tue.mpg.de

We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream. Specifically, we propose a motion vector-based warping method for propagating segmentation masks from keyframes to other frames in a bi-directional and multi-hop manner. Additionally, we introduce a residual-based correction module that can fix wrongly propagated segmentation masks from noisy or erroneous motion vectors. Our approach is flexible and can be added on top of several existing video object segmentation algorithms. We achieved highly competitive results on DAVIS17 and YouTube-VOS on various base models with substantial speed-ups of up to 3.5X with minor drops in accuracy.

The recently developed DEtection TRansformer (DETR) establishes a new object detection paradigm by eliminating a series of hand-crafted components. However, DETR suffers from extremely slow convergence, which increases the training cost significantly. We observe that the slow convergence is largely attributed to the complication in matching object queries with target features in different feature embedding spaces. This paper presents SAM-DETR, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy. SAM-DETR addresses the convergence issue from two perspectives. First, it projects object queries into the same embedding space as encoded image features, where the matching can be accomplished efficiently with aligned semantics. Second, it explicitly searches salient points with the most discriminative features for semantic-aligned matching, which further speeds up the convergence and boosts detection accuracy as well. Being like a plug and play, SAM-DETR complements existing convergence solutions well yet only introduces slight computational overhead. Extensive experiments show that the proposed SAM-DETR achieves superior convergence as well as competitive detection accuracy. The implementation codes are publicly available at https://github.com/ZhangGongjie/SAM-DETR.