Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply enlarging receptive field also gives rise to several concerns. On the one hand, using dense attention e.g., in ViT, leads to excessive memory and computational cost, and features can be influenced by irrelevant parts which are beyond the region of interests. On the other hand, the sparse attention adopted in PVT or Swin Transformer is data agnostic and may limit the ability to model long range relations. To mitigate these issues, we propose a novel deformable self-attention module, where the positions of key and value pairs in self-attention are selected in a data-dependent way. This flexible scheme enables the self-attention module to focus on relevant regions and capture more informative features. On this basis, we present Deformable Attention Transformer, a general backbone model with deformable attention for both image classification and dense prediction tasks. Extensive experiments show that our models achieve consistently improved results on comprehensive benchmarks. Code is available at https://github.com/LeapLabTHU/DAT.
University of Science and Technology of China（中国科学技术大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive e…
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare patches within and across frames. These fixed attention schemes not only have high computational cost but, by comparing patches at predetermined locations, they neglect the motion dynamics in the video. In this paper, we introduce the Deformable Video Transformer (DVT), which dynamically predicts a small subset of video patches to attend for each query locat…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；AnyVision；Peking University（北京大学）
Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this problem, we propose a new Deformable Patch (DePatch) module which learns to adaptively split the images into patches with different positions and scales in a data-driven way rather than using predefined fixed patches. In this way, our method can well preserve the semantics in patches. The DePatch module can work as a plug-and-play module, which can easily be in…
Megvii Technology（旷视科技）；University of Electronic Science and Technology of China（电子科技大学）
This work addresses the Burst Super-Resolution (BurstSR) task using a new architecture, which requires restoring a high-quality image from a sequence of noisy, misaligned, and low-resolution RAW bursts. To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction. To achieve this goal, we propose a Pyramid Flow-Guided Deformable Convolution Network (Pyramid FG-DCN) and incorporate Swin Transformer Blocks and Groups as our main backbone. More specifically, we…
Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images. Recently, RefSR has been attracting great attention as it provides an alternative way to surpass single image SR. However, addressing the RefSR problem has two critical challenges: (i) It is difficult to match the correspondence between LR and Ref images when they are significantly different; (ii) How to transfer the relevant texture from Ref images to compensate the details for LR images is very challenging. To address these issues of RefSR, this paper p…
Yonsei University（延世大学）；Korea Institute of Science and Technology (KIST)（韩国科学技术院）
The camouflaged object detection (COD) task aims to identify and segment objects that blend into the background due to their similar color or texture. Despite the inherent difficulties of the task, COD has gained considerable attention in several fields, such as medicine, life-saving, and anti-military fields. In this paper, we propose a novel solution called the Deformable Point Sampling network (DPS-Net) to address the challenges associated with COD. The proposed DPS-Net utilizes a Deformable Point Sampling transformer (DPS transformer) that can effectively capture sparse local boundary info…
University at Buffalo（布法罗大学）；OPPO US Research Center, InnoPeak Technology Inc.（OPPO美国研究中心，InnoPeak科技公司）
Video instance segmentation (VIS) task requires classifying, segmenting, and tracking object instances over all frames in a video clip. Recently, VisTR has been proposed as end-to-end transformer-based VIS framework, while demonstrating state-of-the-art performance. However, VisTR is slow to converge during training, requiring around 1000 GPU hours due to the high computational cost of its transformer attention module. To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temp…
FPT Software AI Center（FPT软件人工智能中心）；John von Neumann Institute, Vietnam National University（越南国家大学冯·诺依曼研究院）；My Duc Phu Nhuan Hospital（美德富润医院）；Vinmec Central Park International Hospital（Vinmec中央公园国际医院）；Arkansas Economic Development Commission（阿肯色州经济发展委员会）；University of Science, VNU-HCM（越南国家大学胡志明市分校科学大学）；University of Arkansas（阿肯色大学）；My Duc Hospital（美德医院）
The timing of cell divisions in early embryos during the In-Vitro Fertilization (IVF) process is a key predictor of embryo viability. However, observing cell divisions in Time-Lapse Monitoring (TLM) is a time-consuming process and highly depends on experts. In this paper, we propose EmbryosFormer, a computational model to automatically detect and classify cell divisions from original time-lapse images. Our proposed network is designed as an encoder-decoder deformable transformer with collaborative heads. The transformer contracting path predicts per-image labels and is optimized by a classific…
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（武汉大学多媒体软件国家工程研究中心）；Hubei Luojia Laboratory（湖北珞珈实验室）；JD Explore Academy（京东探索研究院）
Convolution neural networks (CNNs) and Transformers have their own advantages and both have been widely used for dense prediction in multi-task learning (MTL). Most of the current studies on MTL solely rely on CNN or Transformer. In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer for multi-task learning of dense prediction. Our method, named DeMT, is based on a simple and effective encoder-decoder architecture (i.e., deformable mixer encoder and task-aware transformer decoder). First, the deformable mixer encoder contains two types…
Southeast University（东南大学）；Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing（江苏省医学信息处理联合国际研究实验室）；University of Western Ontario（西安大略大学）
An effective backbone network is important to deep learning-based Deformable Medical Image Registration (DMIR), because it extracts and matches the features between two images to discover the mutual correspondence for fine registration. However, the existing deep networks focus on single image situation and are limited in registration task which is performed on paired images. Therefore, we advance a novel backbone network, XMorpher, for the effective corresponding feature representation in DMIR. 1) It proposes a novel full transformer architecture including dual parallel feature extraction net…
Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. However, most of the polyp segmentation methods require pixel-wise annotated datasets. Annotated datasets are tedious and time-consuming to produce, especially for physicians who must dedicate their time to their patients. We tackle this issue by proposing a novel framework that can be trained using only weakly annotated images along with exploiting unlabeled images. To this end, we propose three ideas to address this problem, more specifically our contributions are: 1) a novel sparse foreground loss th…
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer
Technical University of Kaiserslautern（凯泽斯劳滕工业大学）；German Research Institute for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Luleå University of Technology（吕勒奥理工大学）
A novel, real-time, mm-Wave radar-based static hand shape classification algorithm and implementation are proposed. The method finds several applications in low cost and privacy sensitive touchless control technology using 60 Ghz radar as the sensor input. As opposed to prior Range-Doppler image based 2D classification solutions, our method converts raw radar data to 3D sparse cartesian point clouds.The demonstrated 3D radar neural network model using deformable transformers significantly surpasses the performance results set by prior methods which either utilize custom signal processing or ap…
Johns Hopkins Medical Institutes（约翰斯·霍普金斯医学研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）；NVIDIA Corporation（英伟达公司）
Transformers have recently shown promise for medical image applications, leading to an increasing interest in developing such models for medical image registration. Recent advancements in designing registration Transformers have focused on using cross-attention (CA) to enable a more precise understanding of spatial correspondences between moving and fixed images. Here, we propose a novel CA mechanism that computes windowed attention using deformable windows. In contrast to existing CA mechanisms that require intensive computational complexity by either computing CA globally or locally with a f…
DeGMix: Efficient Multi-Task Dense Prediction with Deformable and Gating Mixer
Department of Computer Science & Technology, Institute for AI, Tsinghua University（计算机科学与技术系，人工智能研究院，清华大学）；School of Computer Science, Wuhan University（计算机科学学院，武汉大学）；King Abdullah University of Science and Technology（卡布斯大学）
Shanghai Jiao Tong University（上海交通大学）；Qingyuan Research Institute, SJTU（上海交通大学清源研究院）；Peking University（北京大学）；Sensetime Research（商汤科技研究院）；UCLA（加州大学洛杉矶分校）
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, an end-to-end video object detection model based on a spatial-temporal Transformer architecture. The goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, …
Technical University of Catalonia（加泰罗尼亚理工大学）；Technical University of Munich（慕尼黑工业大学）
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of these subtasks in their architectural design, hence missing out on a joint solution. Transformers recently allowed to cast the entire VIS task as a single set-prediction problem. Nevertheless, the quadratic complexity of existing Transformer-based methods requires long training times, high memory requirements, and processing of low-single-scale feature maps. Deformable attention provides a more efficient alternative but …
Multi-Scale Deformable Transformers for Student Learning Behavior Detection in Smart Classroom
Central China Normal University（华中师范大学）；CCNU Wollongong Joint Institute, Central China Normal University（华中师范大学伍伦贡联合研究院）；Hubei University of Technology（湖北工业大学）
National Heart and Lung Institute, Imperial College London（帝国理工学院国家心肺研究所）；Cardiovascular Research Centre, Royal Brompton Hospital（皇家布朗普顿医院心血管研究中心）；School of Biomedical Engineering, Sun Yat-sen University（中山大学生物医学工程学院）
Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based models, are fast-growing in natural language processing and promptly developed for computer vision and medical image analysis due to their prominent performance. Nevertheless, due to the complexity of the Transformer, the application of fast MRI may not be straightforward. The main obstacle is the computational cost of the self-attention layer, which is the co…
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
OpenGVLab, Shanghai AI Laboratory（上海人工智能实验室 OpenGVLab）；Tsinghua University（清华大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；Nanjing University（南京大学）；University of Toronto（多伦多大学）；CAIR, HKISI, CAS（中国科学院香港创新研究院人工智能与机器人创新中心）
Huazhong University of Science and Technology（华中科技大学）；College of Life Science and Technology, Huazhong University of Science and Technology（华中科技大学生命科学与技术学院）
Deformable medical image registration plays an important role in clinical diagnosis and treatment. Recently, the deep learning (DL) based image registration methods have been widely investigated and showed excellent performance in computational speed. However, these methods cannot provide enough registration accuracy because of insufficient ability in representing both the global and local features of the moving and fixed images. To address this issue, this paper has proposed the transformer based image registration method. This method uses the distinctive transformer to extract the global and…
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Tsinghua University（清华大学）；Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
UAVD-Mamba: Deformable Token Fusion Vision Mamba for Multimodal UAV Detection
College of Mechanical and Vehicle Engineering, Hunan University（湖南大学机械与车辆工程学院）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
LG AI Research（LG人工智能研究院）；Kakao Brain；Korea University（高丽大学）；Hanyang University（汉阳大学）
Human-Object Interaction (HOI) detection is the task of identifying a set of <human, object, interaction> triplets from an image. Recent work proposed transformer encoder-decoder architectures that successfully eliminated the need for many hand-designed components in HOI detection through end-to-end training. However, they are limited to single-scale feature resolution, providing suboptimal performance in scenes containing humans, objects and their interactions with vastly different scales and distances. To tackle this problem, we propose a Multi-Scale TRansformer (MSTR) for HOI detection powe…
Object detection is one of the most significant aspects of computer vision, and it has achieved substantial results in a variety of domains. It is worth noting that there are few studies focusing on slender object detection. CNNs are widely employed in object detection, however it performs poorly on slender object detection due to the fixed geometric structure and sampling points. In comparison, Deformable DETR has the ability to obtain global to specific features. Even though it outperforms the CNNs in slender objects detection accuracy and efficiency, the results are still not satisfactory. …
Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar methods like masked image modeling in vision transformer and demonstrated improvements in the image classification task. Such simple self-supervised methods are not exhaustively studied for object detection transformers (DETR, Deformable DETR) as their transformer encoder modules take input in the convolutional neural network (CNN) extracted feature space rather t…
Interdisciplinary Program in AI, Seoul National University（首尔国立大学人工智能跨学科项目）；Artificial Intelligence Institute, Seoul National University（首尔国立大学人工智能研究所）；Department of Computer Science, Seoul National University（首尔国立大学计算机科学系）
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Although detection with Transformer (DETR) is increasingly popular, its global attention modeling requires an extremely long training period to optimize and achieve promising detection performance. Alternative to existing studies that mainly develop advanced feature or embedding designs to tackle the training issue, we point out that the Region-of-Interest (RoI) based detection refinement can easily help mitigate the difficulty of training for DETR methods. Based on this, we introduce a novel REcurrent Glimpse-based decOder (REGO) in this paper. In particular, the REGO employs a multi-stage re…
Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, the first end-to-end video object detection system based on spatial-temporal Transformer architectures. The first goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggreg…
Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation
RWTH Aachen University（亚琛工业大学）；Iran University of Science and Technology（伊朗科技大学）；Shahid Beheshti University（沙希德·贝赫什提大学）；Northwestern University（西北大学）；University of Regensburg（雷根斯堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学研究所MEVIS）
Boston University（波士顿大学）；American University in Cairo（开罗美国大学）；Worcester Polytechnic Institute（伍斯特理工学院）；University of Washington（华盛顿大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Less than 35% of recyclable waste is being actually recycled in the US, which leads to increased soil and sea pollution and is one of the major concerns of environmental researchers as well as the common public. At the heart of the problem are the inefficiencies of the waste sorting process (separating paper, plastic, metal, glass, etc.) due to the extremely complex and cluttered nature of the waste stream. Recyclable waste detection poses a unique computer vision challenge as it requires detection of highly deformable and often translucent objects in cluttered scenes without the kind of conte…
ETH Zurich（苏黎世联邦理工学院）；Meta Inc.（Meta公司）；University of Wurzburg（维尔茨堡大学）
Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the video frame by frame in a recurrent way, which would result in different merits and drawbacks. Typically, the former has the advantage of temporal information fusion. However, it suffers from large model size and intensive memory consumption; the latter has a relatively small model size as it shares parameters across frames; however, it lacks long-range depende…
A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search
School of Integrated Circuits, Sun Yat-Sen University, Shenzhen, China（集成电路学院，中山大学，深圳，中国）；School of Electronic Science and Engineering, Nanjing University, Nanjing, China（电子科学与工程学院，南京大学，南京，中国）
针对可变形注意力 Transformer 的不规则内存访问问题，提出结合 NAS 切片策略的硬件友好优化框架，并通过 FPGA 验证其在精度几乎不变时显著降低 DRAM 访问。
