Convolutional Neural Networks (CNNs) have dominated computer vision for years, due to its ability in capturing locality and translation invariance. Recently, many vision transformer architectures have been proposed and they show promising performance. A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies. However, since the current dense self-attention uses all image patches (tokens) to compute attention matrix, it may neglect locality of images patches and involve noisy tokens (e.g., clutter background and occlusion), leading to a slow training process and potential degradation of performance. To address these problems, we propose the $k$-NN attention for boosting vision transformers. Specifically, instead of involving all the tokens for attention matrix calculation, we only select the top-$k$ similar tokens from the keys for each query to compute the attention map. The proposed $k$-NN attention naturally inherits the local bias of CNNs without introducing convolutional operations, as nearby tokens tend to be more similar than others. In addition, the $k$-NN attention allows for the exploration of long range correlation and at the same time filters out irrelevant tokens by choosing the most similar tokens from the entire image. Despite its simplicity, we verify, both theoretically and empirically, that $k$-NN attention is powerful in speeding up training and distilling noise from input tokens. Extensive experiments are conducted by using 11 different vision transformer architectures to verify that the proposed $k$-NN attention can work with any existing transformer architectures to improve its prediction performance. The codes are available at \url{https://github.com/damo-cv/KVT}.
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention. Previous arts extract features from support and query images, which are processed jointly before making predictions on query images. The whole process is based on convolutional neural networks (CNN), leading to the problem that only local information is used. In this paper, we propose a TRansformer-based Few-shot Semantic segmentation method (TRFS). Specifically, our model…
Camouflaged object detection intends to discover the concealed objects hidden in the surroundings. Existing methods follow the bio-inspired framework, which first locates the object and second refines the boundary. We argue that the discovery of camouflaged objects depends on the recurrent search for the object and the boundary. The recurrent processing makes the human tired and helpless, but it is just the advantage of the transformer with global search ability. Therefore, a dual-task interactive transformer is proposed to detect both accurate position of the camouflaged object and its detail…
Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores. Existing methods generally tackle this by hand-crafted or CNN-based methods, which either lack robustness to severe deformations or inherit the limitation of CNNs that fail to discriminate incorrect matches due to limited receptive fields and inadaptability. In this paper, we introduce Cost Aggregation with Transformers (CATs) to tackle this by exploring global consensus among initial correlation map with the help of some architectural designs that allow us to fully enj…
Boosting Hyperspectral Image Classification with Gate-Shift-Fuse Mechanisms in a Novel CNN-Transformer Approach
University of Salento（萨伦托大学）；National Research Council of Italy（意大利国家研究委员会）；Universite Polytechnique Hauts de France（上法兰西理工大学）；Universite de Lille（里尔大学）；CNRS（法国国家科学研究中心）
PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Clouds
School of Mathematics and Computer Science, Nanchang University（南昌大学数学与计算机科学学院）；School of Automation, Southeast University（东南大学自动化学院）；Aberdeen Institute of Data Science and Artificial Intelligence, South China Normal University（华南师范大学 Aberdeen 数据科学与人工智能研究院）；Houmo AI
State Key Laboratory of Virtual Reality Technology and Systems, SCSE, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；Pengcheng Laboratory（鹏城实验室）
Salient object detection requires a comprehensive and scalable receptive field to locate the visually significant objects in the image. Recently, the emergence of visual transformers and multi-branch modules has significantly enhanced the ability of neural networks to perceive objects at different scales. However, compared to the traditional backbone, the calculation process of transformers is time-consuming. Moreover, different branches of the multi-branch modules could cause the same error back propagation in each training iteration, which is not conducive to extracting discriminative featur…
Xi’an Jiaotong University（西安交通大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Science（中国科学院深圳先进技术研究院）；Xiamen University（厦门大学）；Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology（哈尔滨工业大学）
This paper focuses on the challenging crowd counting task. As large-scale variations often exist within crowd images, neither fixed-size convolution kernel of CNN nor fixed-size attention of recent vision transformers can well handle this kind of variation. To address this problem, we propose a Multifaceted Attention Network (MAN) to improve transformer models in local spatial relation encoding. MAN incorporates global attention from a vanilla transformer, learnable local attention, and instance attention into a counting model. Firstly, the local Learnable Region Attention (LRA) is proposed to…
Dealicious Inc.（Dealicious公司）；Institute of Advanced Research on Artificial Intelligence (IARAI)（人工智能高等研究院）；Athena RC（雅典娜研究中心）
Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional networks. We propose a number of improvements that make transformers outperform the state of the art for the first time. (1) We show that a hybrid architecture is more effective than plain transformers, by a large margin. (2) We introduce two branches collecting global (classification token) and local (patch tokens) information, from which we form a global image re…
Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net
Nankai University（南开大学）；Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局）；Institute for Infocomm Research (I2R)（资讯通信研究院）；University of Electronic Science and Technology of China (UESTC)（电子科技大学）
Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息工程学院）；Peng Cheng Laboratory（鹏城实验室）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers
Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing 100190, China, and the University of Chinese Academy of Sciences, Beijing 100049, China（中国科学院计算技术研究所人工智能安全重点实验室，中国科学院（CAS）及中国科学院大学，北京）
Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation
East China University of Science and Technology（华东理工大学）；University of Sydney（悉尼大学）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学技术学院）
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
School of Cyberspace Science and Technology, Beijing Institute of Technology（网络安全科学与技术学院，北京理工大学）；School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）
Boosting 3D Neuron Segmentation with 2D Vision Transformer Pre-trained on Natural Images
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；SEU-ALLEN Joint Center, Institute for Brain and Intelligence, Southeast University（东南大学SEU-ALLEN联合中心脑与智能研究院）
Fudan University（复旦大学）；Digital Medical Research Center（数字医学研究中心）；School of Basic Medical Science（基础医学院）；Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention（上海市医学影像计算与计算机辅助干预重点实验室）
Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task. Inspired by its success, Point-BERT, as a pioneer work in point cloud, proposed masked point modeling (MPM) to pre-train point transformer on large scale unanotated dataset. Despite its great performance, we find the inherent difference between language and point cloud tends to cause ambiguous tokenization for point cloud. For point cloud, there doesn't exist a gold standard for point cloud tokenization. Point-BERT use a discrete Variational AutoEncoder (dVAE) as tokenizer, but it might gene…
Shanghai Jiao Tong University（上海交通大学）；G60 Yun Zhi AI Innovation and Application Research Center（G60云智人工智能创新应用研究中心）；Midea Corporate Research Center（美的集团中央研究院）
We introduce a lightweight network to improve descriptors of keypoints within the same image. The network takes the original descriptors and the geometric properties of keypoints as the input, and uses an MLP-based self-boosting stage and a Transformer-based cross-boosting stage to enhance the descriptors. The boosted descriptors can be either real-valued or binary ones. We use the proposed network to boost both hand-crafted (ORB, SIFT) and the state-of-the-art learning-based descriptors (SuperPoint, ALIKE) and evaluate them on image matching, visual localization, and structure-from-motion tas…
Department of Forest Sciences, University of Helsinki（赫尔辛基大学森林科学系）；School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China（武汉大学计算机学院、国家多媒体软件工程研究中心、人工智能研究院、湖北省多媒体与网络通信工程重点实验室，武汉，中国）
We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of content features by considering context information through a self-attention module in Transformers. By augmenting such tokens with an instance-level feature extracted from the content feature with respect to bounding box information, our framework is capable of learning an interaction between object…
Although transformer networks are recently employed in various vision tasks with outperforming performance, extensive training data and a lengthy training time are required to train a model to disregard an inductive bias. Using trainable links between the channel-wise spatial attention of a pre-trained Convolutional Neural Network (CNN) and the attention head of Vision Transformers (ViT), we present a regularization technique to improve the training efficiency of ViT. The trainable links are referred to as the attention augmentation module, which is trained simultaneously with ViT, boosting th…
VistaRef: Boosting Visual Spatial Orientation Awareness for Pointing-to-Object Detection
Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Dalian University of Technology（大连理工大学）
Convolutional neural networks (CNNs) and transformers, which are composed of multiple processing layers and blocks to learn the representations of data with multiple abstract levels, are the most successful machine learning models in recent years. However, millions of parameters and many blocks make them difficult to be trained, and sometimes several days or weeks are required to find an ideal architecture or tune the parameters. Within this paper, we propose a new algorithm for boosting Deep Convolutional Neural Networks (BoostCNN) to combine the merits of dynamic feature selection and BoostC…
We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robustness and strengthens privacy. We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer. The stochastic parameters are sampled from the uniform distribution, both during training and inference. The applied linear operations preserve the topological structure, formed by the set of tokens passing through the shared mult…
UC Santa Cruz（加州大学圣克鲁兹分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
The recent success of Vision Transformers is shaking the long dominance of Convolutional Neural Networks (CNNs) in image recognition for a decade. Specifically, in terms of robustness on out-of-distribution samples, recent research finds that Transformers are inherently more robust than CNNs, regardless of different training setups. Moreover, it is believed that such superiority of Transformers should largely be credited to their self-attention-like architectures per se. In this paper, we question that belief by closely examining the design of Transformers. Our findings lead to three highly ef…
Little Strokes Fell Great Oaks: Boosting the Hierarchical Features for Multi-exposure Image Fusion
College of Computer Science and Technology, Zhejiang University of Technology（浙江工业大学计算机科学与技术学院）；School of Mechanical Engineering, Dalian University of Technology（大连理工大学机械工程学院）
University of Electronic Science and Technology of China（电子科技大学）
Due to the gap between a substitute model and a victim model, the gradient-based noise generated from a substitute model may have low transferability for a victim model since their gradients are different. Inspired by the fact that the decision boundaries of different models do not differ much, we conduct experiments and discover that the gradients of different models are more similar on the decision boundary than in the original position. Moreover, since the decision boundary in the vicinity of an input image is flat along most directions, we conjecture that the boundary gradients can help fi…
The paper describes our proposed methodology for the six basic expression classification track of Affective Behavior Analysis in-the-wild (ABAW) Competition 2022. In Learing from Synthetic Data(LSD) task, facial expression recognition (FER) methods aim to learn the representation of expression from the artificially generated data and generalise to real data. Because of the ambiguous of the synthetic data and the objectivity of the facial Action Unit (AU), we resort to the AU information for performance boosting, and make contributions as follows. First, to adapt the model to synthetic scenario…
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
Archimedes, Athena RC National Technical University of Athens（阿提卡RC机构，国家技术大学雅典）；IIT, NCSR "Demokritos"（IIT，NCSR "德摩多罗斯"）；University of Crete IACM-Forth（克里特大学IACM-第四研究机构）
Vision transformers (ViTs) have been an alternative design paradigm to convolutional neural networks (CNNs). However, the training of ViTs is much harder than CNNs, as it is sensitive to the training parameters, such as learning rate, optimizer and warmup epoch. The reasons for training difficulty are empirically analysed in ~\cite{xiao2021early}, and the authors conjecture that the issue lies with the \textit{patchify-stem} of ViT models and propose that early convolutions help transformers see better. In this paper, we further investigate this problem and extend the above conclusion: only ea…
Text-VQA aims at answering questions that require understanding the textual cues in an image. Despite the great progress of existing Text-VQA methods, their performance suffers from insufficient human-labeled question-answer (QA) pairs. However, we observe that, in general, the scene text is not fully exploited in the existing datasets -- only a small portion of the text in each image participates in the annotated QA activities. This results in a huge waste of useful information. To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly uti…
The University of Adelaide（阿德莱德大学）；Adobe Inc.（Adobe公司）；Zhejiang University（浙江大学）
Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either refine the trimaps or adapt the algorithms to real-world images via extra data augmentation, none of them has taken both into consideration, not to mention the significant performance deterioration on benchmarks while using those data augmentation. To fill this gap, we propose an image matting method w…
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined training for 3D foreground/background segmentation, cylindrical object proposals, and point completion. Furthermore, they often overlook the inter-object feature relation that is particularly informative to hard samples for 3D annotation. To this end, we propose a simple yet effective end-to-end Context-Aware Transformer (CAT) as an automated 3D-box labeler to generate precise 3D box annotations from 2D boxes, traine…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Fine-grained visual categorization (FGVC) aims at recognizing objects from similar subordinate categories, which is challenging and practical for human's accurate automatic recognition needs. Most FGVC approaches focus on the attention mechanism research for discriminative regions mining while neglecting their interdependencies and composed holistic object structure, which are essential for model's discriminative information localization and understanding ability. To address the above limitations, we propose the Structure Information Modeling Transformer (SIM-Trans) to incorporate object struc…
LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging
Nanjing University of Posts and Telecommunications（南京邮电大学）；Horizon Robotics；Nanjing University（南京大学）；Zhejiang University（浙江大学）；Macau University of Science and Technology（澳门科技大学）；TARS Robotics；China Mobile Zijin Innovation Institute（中国移动吉林创新研究院）
Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. Although rotated anchors have been used to tackle this problem, the design…
University of Chinese Academy of Sciences（中国科学院大学）；Chinese Academy of Sciences（中国科学院）；West Virginia University（西弗吉尼亚大学）；Baidu Research（百度研究院）
Facial Expression Recognition (FER) in the wild is an extremely challenging task. Recently, some Vision Transformers (ViT) have been explored for FER, but most of them perform inferiorly compared to Convolutional Neural Networks (CNN). This is mainly because the new proposed modules are difficult to converge well from scratch due to lacking inductive bias and easy to focus on the occlusion and noisy areas. TransFER, a representative transformer-based method for FER, alleviates this with multi-branch attention dropping but brings excessive computations. On the contrary, we present two attentive…
Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations
Tsinghua University（清华大学）；College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Microsoft Research Asia（微软亚洲研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Fudan University（复旦大学）；Oracle Health and AI（甲骨文健康与人工智能部门）；Shanghai AI Laboratory（上海人工智能实验室）
Few-shot fine-grained learning aims to classify a query image into one of a set of support categories with fine-grained differences. Although learning different objects' local differences via Deep Neural Networks has achieved success, how to exploit the query-support cross-image object semantic relations in Transformer-based architecture remains under-explored in the few-shot fine-grained scenario. In this work, we propose a Transformer-based double-helix model, namely HelixFormer, to achieve the cross-image object semantic relation mining in a bidirectional and symmetrical manner. The HelixFo…
