DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting
South China University of Technology（华南理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；Tsinghua University（清华大学）
In this paper, we propose a new operator, called 3D DeFormable Attention (DFA3D), for 2D-to-3D feature lifting, which transforms multi-view 2D image features into a unified 3D space for 3D object detection. Existing feature lifting approaches, such as Lift-Splat-based and 2D attention-based, either use estimated depth to get pseudo LiDAR features and then splat them to a 3D space, which is a one-pass operation without feature refinement, or ignore depth and lift features by 2D attention mechanisms, which achieve finer semantics while suffering from a depth ambiguity problem. In contrast, our DFA3D-based method first leverages the estimated depth to expand each view's 2D feature map to 3D and then utilizes DFA3D to aggregate features from the expanded 3D feature maps. With the help of DFA3D, the depth ambiguity problem can be effectively alleviated from the root, and the lifted features can be progressively refined layer by layer, thanks to the Transformer-like architecture. In addition, we propose a mathematically equivalent implementation of DFA3D which can significantly improve its memory efficiency and computational speed. We integrate DFA3D into several methods that use 2D attention-based feature lifting with only a few modifications in code and evaluate on the nuScenes dataset. The experiment results show a consistent improvement of +1.41\% mAP on average, and up to +15.1\% mAP improvement when high-quality depth information is available, demonstrating the superiority, applicability, and huge potential of DFA3D. The code is available at https://github.com/IDEA-Research/3D-deformable-attention.git.
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…
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. …
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…
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）
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）
Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing. Here we propose a novel end-to-end instance segmentation method termed ISDA. It reshapes the task into predicting a set of object masks, which are generated via traditional convolution operation with learned position-aware kernels and features of objects. Such kernels and features are learned by leveraging a deformable attention network with multi-scale representation. Thanks to the introduced set-…
Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection
School of Electrical and Information Engineering, Jiangsu University（江苏大学电气与信息工程学院）；School of Computer Science and Engineering, Jiangsu University of Science and Technology（江苏科技大学计算机科学与工程学院）
DAUNet: A Lightweight UNet Variant with Deformable Convolutions and Parameter-Free Attention for Medical Image Segmentation
Department of Electrical Engineering (ISY), Information Coding (ICG), Linköping University（电气工程系（ISY）、信息编码系（ICG）、利厄普大学）；SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum & Minerals（SDAIA-KFUPM人工智能联合研究中心、国王法赫德石油大学）；Department of Computer Engineering, College of Computing and Mathematics, King Fahd University of Petroleum & Minerals（计算机工程系、计算与数学学院、国王法赫德石油大学）
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…
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）
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 …
DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR, enhances the efficiency of DETR by replacing dense attention with deformable attention, which achieves 10x faster convergence and improved performance. Deformable DETR uses the multiscale feature to ameliorate performance, however, the number of encoder tokens increases by 20x compared to DETR, and the computation cost of the encoder attention remains a bottl…
Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects subject to different transformations; these require many parameters. Sampling equivariant networks can adjust sampling from input feature maps according to the transformation of the object, allowing a kernel to extract features of an object under different transformations. Doing so requires fewer parameters, and makes the network more suitable for represent…
Trinity College Dublin（都柏林圣三一学院）；Accenture Labs（埃森哲实验室）
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically require some manual input to define the relationships between different body joints. We propose a novel transformer-based approach that uses the more generalised self-attention mechanism to learn these relationships within a sequence of tokens representing joints. We find that the use of intermediate supervision, as well as residual connections between the …
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Department of Physics, J.K. Institute of Science（J.K.科学研究所物理系）；World Scientific University（世界科学出版社大学）；University of Intelligent Studies（智能研究大学）；School of Computer and Electronic Information, Nanjing Normal University（南京师范大学计算机与电子信息学院）
Hanyang University（汉阳大学）；Korea Advanced Institute of Science & Technology (KAIST)（韩国科学技术院（KAIST））
Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection. One key challenge in camera-LiDAR fusion involves mitigating the large domain gap between the two sensors in terms of coordinates and data distribution when fusing their features. In this paper, we propose a novel camera-LiDAR fusion architecture called, 3D Dual-Fusion, which is designed to mitigate the gap between the feature representations of camera and LiDAR data. The proposed method fuses the features of the camera-view and 3D voxel-view domain and models their interactions through …
Tsinghua University（清华大学）；BNRist（北京国家信息科学与技术研究中心）；Amazon（亚马逊）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）
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 li…
Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；University of Maryland（马里兰大学）；Shanghai Jiao Tong University（上海交通大学）；Guangdong University of Foreign Studies（广东外语外贸大学）；WINNER Technology
We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density Map Estimator (DME) then generates high-quality density maps. With the attention-aware training scheme…
Siamese-based trackers have achieved excellent performance on visual object tracking. However, the target template is not updated online, and the features of the target template and search image are computed independently in a Siamese architecture. In this paper, we propose Deformable Siamese Attention Networks, referred to as SiamAttn, by introducing a new Siamese attention mechanism that computes deformable self-attention and cross-attention. The self attention learns strong context information via spatial attention, and selectively emphasizes interdependent channel-wise features with channe…
Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image. Existing methods usually build up multi-stage frameworks to deal with clothes warping and body blending respectively, or rely heavily on intermediate parser-based labels which may be noisy or even inaccurate. To solve the above challenges, we propose a single-stage try-on framework by developing a novel Deformable Attention Flow (DAFlow), which applies the deformable attention scheme to multi-flow estimation. With pose keypoints as the guidance only, the self- and cross-defor…
Megvii Technology（旷视科技）；Sichuan University（四川大学）；University of Electronic Science and Technology of China（电子科技大学）
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet. This problem comprises two intractable challenges of how to handle saturation and noise properly and how to tackle misalignments caused by object motion or camera jittering. To address the former, we adopt a spatial attention module to adaptively select the most appropriate regions of various exposure low dynamic range (LDR) images for fusion. For the latter one, we propose to align the gamma-corrected images in the feature-level with a Pyrami…
West Virginia University（西弗吉尼亚大学）；Huazhong University of Science and Technology（华中科技大学）
Video super-resolution, which attempts to reconstruct high-resolution video frames from their corresponding low-resolution versions, has received increasingly more attention in recent years. Most existing approaches opt to use deformable convolution to temporally align neighboring frames and apply traditional spatial attention mechanism (convolution based) to enhance reconstructed features. However, such spatial-only strategies cannot fully utilize temporal dependency among video frames. In this paper, we propose a novel deep learning based VSR algorithm, named Deformable Kernel Spatial Attent…
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…
Harbin Institute of Technology（哈尔滨工业大学）；Tencent AI Lab（腾讯人工智能实验室）
The key success factor of the video deblurring methods is to compensate for the blurry pixels of the mid-frame with the sharp pixels of the adjacent video frames. Therefore, mainstream methods align the adjacent frames based on the estimated optical flows and fuse the alignment frames for restoration. However, these methods sometimes generate unsatisfactory results because they rarely consider the blur levels of pixels, which may introduce blurry pixels from video frames. Actually, not all the pixels in the video frames are sharp and beneficial for deblurring. To address this problem, we propo…
A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Tianjin University（天津大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）；Linköping University（林雪平大学）
S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
Hunan Vanguard Group Corporation Limited（湖南先锋集团有限公司）；College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机与通信工程学院）；School of Robotics, Hunan University（湖南大学机器人学院）
Georgia Institute of Technology（佐治亚理工学院）；Tencent AI Lab（腾讯人工智能实验室）
Capturing contextual dependencies has proven useful to improve the representational power of deep neural networks. Recent approaches that focus on modeling global context, such as self-attention and non-local operation, achieve this goal by enabling unconstrained pairwise interactions between elements. In this work, we consider learning representations for deformable objects which can benefit from context exploitation by modeling the structural dependencies that the data intrinsically possesses. To this end, we provide a novel structure-regularized attention mechanism, which formalizes feature…
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…
Nanjing University of Posts and Telecommunications（南京邮电大学）；University of Trento（特伦托大学）；Wuhan University（武汉大学）
Learning to generate natural scenes has always been a daunting task in computer vision. This is even more laborious when generating images with very different views. When the views are very different, the view fields have little overlap or objects are occluded, leading the task very challenging. In this paper, we propose to use Generative Adversarial Networks(GANs) based on a deformable convolution and attention mechanism to solve the problem of cross-view image synthesis (see Fig.1). It is difficult to understand and transform scenes appearance and semantic information from another view, thus…
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…
Vector Field Attention for Deformable Image Registration
Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins School of Medicine（约翰斯·霍普金斯医学院）；National Institute on Aging（美国国家老龄化研究所）；National Institute of Health（美国国立卫生研究院）
