CVPR 2022 论文列表

Recently, memory-based approaches show promising results on semi-supervised video object segmentation. These methods predict object masks frame-by-frame with the help of frequently updated memory of the previous mask. Different from this per-frame inference, we investigate an alternative perspective by treating video object segmentation as clip-wise mask propagation. In this per-clip inference scheme, we update the memory with an interval and simultaneously process a set of consecutive frames (i.e. clip) between the memory updates. The scheme provides two potential benefits: accuracy gain by clip-level optimization and efficiency gain by parallel computation of multiple frames. To this end, we propose a new method tailored for the per-clip inference. Specifically, we first introduce a clip-wise operation to refine the features based on intra-clip correlation. In addition, we employ a progressive matching mechanism for efficient information-passing within a clip. With the synergy of two modules and a newly proposed per-clip based training, our network achieves state-of-the-art performance on Youtube-VOS 2018/2019 val (84.6% and 84.6%) and DAVIS 2016/2017 val (91.9% and 86.1%). Furthermore, our model shows a great speed-accuracy trade-off with varying memory update intervals, which leads to huge flexibility.

Face anti-spoofing (FAS) plays a critical role in securing face recognition systems from different presentation attacks. Previous works leverage auxiliary pixel-level supervision and domain generalization approaches to address unseen spoof types. However, the local characteristics of image captures, i.e., capturing devices and presenting materials, are ignored in existing works and we argue that such information is required for networks to discriminate between live and spoof images. In this work, we propose PatchNet which reformulates face anti-spoofing as a fine-grained patch-type recognition problem. To be specific, our framework recognizes the combination of capturing devices and presenting materials based on the patches cropped from non-distorted face images. This reformulation can largely improve the data variation and enforce the network to learn discriminative feature from local capture patterns. In addition, to further improve the generalization ability of the spoof feature, we propose the novel Asymmetric Margin-based Classification Loss and Self-supervised Similarity Loss to regularize the patch embedding space. Our experimental results verify our assumption and show that the model is capable of recognizing unseen spoof types robustly by only looking at local regions. Moreover, the fine-grained and patch-level reformulation of FAS outperforms the existing approaches on intra-dataset, cross-dataset, and domain generalization benchmarks. Furthermore, our PatchNet framework can enable practical applications like Few-Shot Reference-based FAS and facilitate future exploration of spoof-related intrinsic cues.

The point cloud learning community is witnesses a modeling shift from CNNs to Transformers, where pure Transformer architectures have achieved top accuracy on the major learning benchmarks. However, existing point Transformers are computationally expensive since they need to generate a large attention map, which has quadratic complexity (both in space and time) with respect to input size. To solve this shortcoming, we introduce patch-attention (PAT) to adaptively learn a much smaller set of bases upon which the attention maps are computed. By a weighted summation upon these bases, PAT not only captures the global shape context but also achieves linear complexity to input size. In addition, we propose a lightweight Multi-Scale Attention (MST) block to build attentions among features of different scales, providing the model with multi-scale features. Equipped with the PAT and MST, we construct our neural architecture called PatchFormer that integrates both modules into a joint framework for point cloud learning. Extensive experiments demonstrate that our network achieves comparable accuracy on general point cloud learning tasks with 9.2x speed-up than previous point Transformers.

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique characteristic of ViT is that it takes a sequence of disjoint patches from an image and processes patch-level representations internally. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. To be specific, we enforce invariance against each patch and its neighbors, i.e., each patch treats similar neighboring patches as positive samples. Consequently, training ViTs with SelfPatch learns more semantically meaningful relations among patches (without using human-annotated labels), which can be beneficial, in particular, to downstream tasks of a dense prediction type. Despite its simplicity, we demonstrate that it can significantly improve the performance of existing SSL methods for various visual tasks, including object detection and semantic segmentation. Specifically, SelfPatch significantly improves the recent self-supervised ViT, DINO, by achieving +1.3 AP on COCO object detection, +1.2 AP on COCO instance segmentation, and +2.9 mIoU on ADE20K semantic segmentation.

This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm. We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers. For each layer, the impact of a patch on the final output feature is approximated and patches with less impacts will be removed. Experimental results on benchmark datasets demonstrate that the proposed method can significantly reduce the computational costs of vision transformers without affecting their performances. For example, over 45% FLOPs of the ViT-Ti model can be reduced with only 0.2% top-1 accuracy drop on the ImageNet dataset.

Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data. In this paper, we explore more challenging exemplar-based high-resolution portrait style transfer by introducing a novel DualStyleGAN with flexible control of dual styles of the original face domain and the extended artistic portrait domain. Different from StyleGAN, DualStyleGAN provides a natural way of style transfer by characterizing the content and style of a portrait with an intrinsic style path and a new extrinsic style path, respectively. The delicately designed extrinsic style path enables our model to modulate both the color and complex structural styles hierarchically to precisely pastiche the style example. Furthermore, a novel progressive fine-tuning scheme is introduced to smoothly transform the generative space of the model to the target domain, even with the above modifications on the network architecture. Experiments demonstrate the superiority of DualStyleGAN over state-of-the-art methods in high-quality portrait style transfer and flexible style control.

We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene sketch does not necessarily contain all objects in the corresponding photo, due to the subjective holistic interpretation of scenes, (ii) there exists significant empty (white) regions as a result of object-level abstraction, and as a result, (iii) existing scene-level fine-grained sketch-based image retrieval methods collapse as scene sketches become more partial. To solve this "partial" problem, we advocate for a simple set-based approach using optimal transport (OT) to model cross-modal region associativity in a partially-aware fashion. Importantly, we improve upon OT to further account for holistic partialness by comparing intra-modal adjacency matrices. Our proposed method is not only robust to partial scene-sketches but also yields state-of-the-art performance on existing datasets.

Current attention-based methods for semantic segmentation mainly model pixel relation through pairwise affinity and coarse segmentation. For the first time, this paper explores modeling pixel relation via Class Activation Map (CAM). Beyond the previous CAM generated from image-level classification, we present Partial CAM, which subdivides the task into region-level prediction and achieves better localization performance. In order to eliminate the intra-class inconsistency caused by the variances of local context, we further propose Partial Class Activation Attention (PCAA) that simultaneously utilizes local and global class-level representations for attention calculation. Once obtained the partial CAM, PCAA collects local class centers and computes pixel-to-class relation locally. Applying local-specific representations ensures reliable results under different local contexts. To guarantee global consistency, we gather global representations from all local class centers and conduct feature aggregation. Experimental results confirm that Partial CAM outperforms the previous two strategies as pixel relation. Notably, our method achieves state-of-the-art performance on several challenging benchmarks including Cityscapes, Pascal Context, and ADE20K. Code is available at https://github.com/lsa1997/PCAA.

We introduce PartGlot, a neural framework and associated architectures for learning semantic part segmentation of 3D shape geometry, based solely on part referential language. We exploit the fact that linguistic descriptions of a shape can provide priors on the shape's parts -- as natural language has evolved to reflect human perception of the compositional structure of objects, essential to their recognition and use. For training we use the paired geometry / language data collected in the ShapeGlot work for their reference game, where a speaker creates an utterance to differentiate a target shape from two distractors and the listener has to find the target based on this utterance. Our network is designed to solve this target discrimination problem, carefully incorporating a Transformer-based attention module so that the output attention can precisely highlight the semantic part or parts described in the language. Furthermore, the network operates without any direct supervision on the 3D geometry itself. Surprisingly, we further demonstrate that the learned part information is generalizable to shape classes unseen during training.Our approach opens the possibility of learning 3D shape parts from language alone, without the need for large-scale part geometry annotations, thus facilitating annotation acquisition.

Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and deteriorate the accuracy. To overcome this problem, several pseudo-label refinement methods have been proposed, but they neglect the fine-grained local context essential for person re-ID. In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between global and part features. Specifically, we design a cross agreement score as the similarity of k-nearest neighbors between feature spaces to exploit the reliable complementary relationship. Based on the cross agreement, we refine pseudo-labels of global features by ensembling the predictions of part features, which collectively alleviate the noise in global feature clustering. We further refine pseudo-labels of part features by applying label smoothing according to the suitability of given labels for each part. Thanks to the reliable complementary information provided by the cross agreement score, our PPLR effectively reduces the influence of noisy labels and learns discriminative representations with rich local contexts. Extensive experimental results on Market-1501 and MSMT17 demonstrate the effectiveness of the proposed method over the state-of-the-art performance. The code is available at https://github.com/yoonkicho/PPLR.

Self-Attention is a widely used building block in neural modeling to mix long-range data elements. Most self-attention neural networks employ pairwise dot-products to specify the attention coefficients. However, these methods require O(N^2) computing cost for sequence length N. Even though some approximation methods have been introduced to relieve the quadratic cost, the performance of the dot-product approach is still bottlenecked by the low-rank constraint in the attention matrix factorization. In this paper, we propose a novel scalable and effective mixing building block called Paramixer. Our method factorizes the interaction matrix into several sparse matrices, where we parameterize the non-zero entries by MLPs with the data elements as input. The overall computing cost of the new building block is as low as O(N \log N). Moreover, all factorizing matrices in Paramixer are full-rank, so it does not suffer from the low-rank bottleneck. We have tested the new method on both synthetic and various real-world long sequential data sets and compared it with several state-of-the-art attention networks. The experimental results show that Paramixer has better performance in most learning tasks.

The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations compared to other non-learned representations and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering transform are typically selected to create a tight frame via a parameterized mother wavelet. In this work, we investigate whether this standard wavelet filterbank construction is optimal. Focusing on Morlet wavelets, we propose to learn the scales, orientations, and aspect ratios of the filters to produce problem-specific parameterizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains in small-sample classification settings over the standard scattering transform. Moreover, our empirical results suggest that traditional filterbank constructions may not always be necessary for scattering transforms to extract effective representations.

Training state-of-the-art vision models has become prohibitively expensive for researchers and practitioners. For the sake of accessibility and resource reuse, it is important to focus on adapting these models to a variety of downstream scenarios. An interesting and practical paradigm is online test-time adaptation, according to which training data is inaccessible, no labelled data from the test distribution is available, and adaptation can only happen at test time and on a handful of samples. In this paper, we investigate how test-time adaptation methods fare for a number of pre-trained models on a variety of real-world scenarios, significantly extending the way they have been originally evaluated. We show that they perform well only in narrowly-defined experimental setups and sometimes fail catastrophically when their hyperparameters are not selected for the same scenario in which they are being tested. Motivated by the inherent uncertainty around the conditions that will ultimately be encountered at test time, we propose a particularly "conservative" approach, which addresses the problem with a Laplacian Adjusted Maximum-likelihood Estimation (LAME) objective. By adapting the model's output (not its parameters), and solving our objective with an efficient concave-convex procedure, our approach exhibits a much higher average accuracy across scenarios than existing methods, while being notably faster and have a much lower memory footprint. The code is available at https://github.com/fiveai/LAME.

This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth regression head to panoptic segmentation (PS) networks, resulting in two independent task branches. This neglects the mutually-beneficial relations between these two tasks, thus failing to exploit handy instance-level semantic cues to boost depth accuracy while also producing sub-optimal depth maps. To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks. Specifically, instead of predicting depth for all pixels at a time, we generate instance-specific kernels to predict depth and segmentation masks for each instance. Moreover, leveraging the instance-wise depth estimation scheme, we add additional instance-level depth cues to assist with supervising the depth learning via a new depth loss. Extensive experiments on Cityscapes-DPS and SemKITTI-DPS show the effectiveness and promise of our method. We hope our unified solution to DPS can lead a new paradigm in this area.

As a rising task, panoptic segmentation is faced with challenges in both semantic segmentation and instance segmentation. However, in terms of speed and accuracy, existing LiDAR methods in the field are still limited. In this paper, we propose a fast and high-performance LiDAR-based framework, referred to as Panoptic-PHNet, with three attractive aspects: 1) We introduce a clustering pseudo heatmap as a new paradigm, which, followed by a center grouping module, yields instance centers for efficient clustering without object-level learning tasks. 2) A knn-transformer module is proposed to model the interaction among foreground points for accurate offset regression. 3) For backbone design, we fuse the fine-grained voxel features and the 2D Bird's Eye View (BEV) features with different receptive fields to utilize both detailed and global information. Extensive experiments on both SemanticKITTI dataset and nuScenes dataset show that our Panoptic-PHNet surpasses state-of-the-art methods by remarkable margins with a real-time speed. We achieve the 1st place on the public leaderboard of SemanticKITTI and leading performance on the recently released leaderboard of nuScenes.

This paper presents a novel framework to integrate both semantic and instance contexts for panoptic segmentation. In existing works, it is common to use a shared backbone to extract features for both things (countable classes such as vehicles) and stuff (uncountable classes such as roads). This, however, fails to capture the rich relations among them, which can be utilized to enhance visual understanding and segmentation performance. To address this shortcoming, we propose a novel Panoptic, Instance, and Semantic Relations (PISR) module to exploit such contexts. First, we generate panoptic encodings to summarize key features of the semantic classes and predicted instances. A Panoptic Relational Attention (PRA) module is then applied to the encodings and the global feature map from the backbone. It produces a feature map that captures 1) the relations across semantic classes and instances and 2) the relations between these panoptic categories and spatial features. PISR also automatically learns to focus on the more important instances, making it robust to the number of instances used in the relational attention module. Moreover, PISR is a general module that can be applied to any existing panoptic segmentation architecture. Through extensive evaluations on panoptic segmentation benchmarks like Cityscapes, COCO, and ADE20K, we show that PISR attains considerable improvements over existing approaches.

Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic segmentation with transformers. It contains three innovative components: an efficient deeply-supervised mask decoder, a query decoupling strategy, and an improved post-processing method. We also use Deformable DETR to efficiently process multi-scale features, which is a fast and efficient version of DETR. Specifically, we supervise the attention modules in the mask decoder in a layer-wise manner. This deep supervision strategy lets the attention modules quickly focus on meaningful semantic regions. It improves performance and reduces the number of required training epochs by half compared to Deformable DETR. Our query decoupling strategy decouples the responsibilities of the query set and avoids mutual interference between things and stuff. In addition, our post-processing strategy improves performance without additional costs by jointly considering classification and segmentation qualities to resolve conflicting mask overlaps. Our approach increases the accuracy 6.2% PQ over the baseline DETR model. Panoptic SegFormer achieves state-of-the-art results on COCO test-dev with 56.2% PQ. It also shows stronger zero-shot robustness over existing methods.

We present PanopticNeRF, an object-aware neural scene representation that decomposes a scene into a set of objects (things) and background (stuff). Each object is represented by a separate MLP that takes a position, direction, and time and outputs density and radiance. The background is represented by a similar MLP that also outputs semantics. Importantly, the object MLPs are specific to each instance and initialized with meta-learning, and thus can be smaller and faster than previous object-aware approaches, while still leveraging category-specific priors. We propose a system to infer the PanopticNeRF representation from a set of color images. We use off-the-shelf algorithms to predict camera poses, object bounding boxes, object categories, and 2D image semantic segmentations. Then we jointly optimize the MLP weights and bounding box parameters using analysis-by-synthesis with self-supervision from the color images and pseudo-supervision from predicted semantic segmentations. PanopticNeRF can be effectively used for multiple 2D and 3D tasks like 3D scene editing, 3D panoptic reconstruction, novel view and semantic synthesis, 2D panoptic segmentation, and multiview depth prediction. We demonstrate these applications on several difficult, dynamic scenes with moving objects.

Existing approaches for learning local image descriptors have shown remarkable achievements in a wide range of geometric tasks. However, most of them require per-pixel correspondence-level supervision, which is difficult to acquire at scale and in high quality. In this paper, we propose to explicitly integrate two matching priors in a single loss in order to learn local descriptors without supervision. Given two images depicting the same scene, we extract pixel descriptors and build a correlation volume. The first prior enforces the local consistency of matches in this volume via a pyramidal structure iteratively constructed using a non-parametric module. The second prior exploits the fact that each descriptor should match with at most one descriptor from the other image. We combine our unsupervised loss with a standard self-supervised loss trained from synthetic image augmentations. Feature descriptors learned by the proposed approach outperform their fully- and self-supervised counterparts on various geometric benchmarks such as visual localization and image matching, achieving state-of-the-art performance. Project webpage: https://europe.naverlabs.com/research/3d-vision/pump