This work aims to improve the efficiency of vision transformers (ViT). While ViTs use computationally expensive self-attention operations in every layer, we identify that these operations are highly correlated across layers -- a key redundancy that causes unnecessary computations. Based on this observation, we propose SkipAt, a method to reuse self-attention computation from preceding layers to approximate attention at one or more subsequent layers. To ensure that reusing self-attention blocks across layers does not degrade the performance, we introduce a simple parametric function, which outperforms the baseline transformer's performance while running computationally faster. We show the effectiveness of our method in image classification and self-supervised learning on ImageNet-1K, semantic segmentation on ADE20K, image denoising on SIDD, and video denoising on DAVIS. We achieve improved throughput at the same-or-higher accuracy levels in all these tasks.
Northeastern University（东北大学）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University（东北大学医学影像智能计算教育部重点实验室）；Amii, University of Alberta（阿尔伯塔大学阿尔伯塔机器智能研究所）
Most recent semantic segmentation methods adopt a U-Net framework with an encoder-decoder architecture. It is still challenging for U-Net with a simple skip connection scheme to model the global multi-scale context: 1) Not each skip connection setting is effective due to the issue of incompatible feature sets of encoder and decoder stage, even some skip connection negatively influence the segmentation performance; 2) The original U-Net is worse than the one without any skip connection on some datasets. Based on our findings, we propose a new segmentation framework, named UCTransNet (with a pro…
Xiamen University（厦门大学）；The University of Hong Kong（香港大学）；Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）深圳大数据研究院）
Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to overcome their inherent shortcomings of spatial inductive bias. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer, a 3D transformer for volumetric medical i…
RWTH Aachen University（亚琛工业大学）；University of Greenwich（格林威治大学）；Iran University of Science and Technology（伊朗科技大学）
In the past few years, convolutional neural networks (CNNs), particularly U-Net, have been the prevailing technique in the medical image processing era. Specifically, the seminal U-Net, as well as its alternatives, have successfully managed to address a wide variety of medical image segmentation tasks. However, these architectures are intrinsically imperfect as they fail to exhibit long-range interactions and spatial dependencies leading to a severe performance drop in the segmentation of medical images with variable shapes and structures. Transformers, preliminary proposed for sequence-to-seq…
Technische Universität München（慕尼黑工业大学）；Fudan University（复旦大学）；Huawei Technologies（华为技术有限公司）
In the past few years, convolutional neural networks (CNNs) have achieved milestones in medical image analysis. Especially, the deep neural networks based on U-shaped architecture and skip-connections have been widely applied in a variety of medical image tasks. However, although CNN has achieved excellent performance, it cannot learn global and long-range semantic information interaction well due to the locality of the convolution operation. In this paper, we propose Swin-Unet, which is an Unet-like pure Transformer for medical image segmentation. The tokenized image patches are fed into the …
Harbin Institute of Technology（哈尔滨工业大学）；Nanyang Technological University（南洋理工大学）
Accurate segmentation of organs or lesions from medical images is crucial for reliable diagnosis of diseases and organ morphometry. In recent years, convolutional encoder-decoder solutions have achieved substantial progress in the field of automatic medical image segmentation. Due to the inherent bias in the convolution operations, prior models mainly focus on local visual cues formed by the neighboring pixels, but fail to fully model the long-range contextual dependencies. In this paper, we propose a novel Transformer-based Attention Guided Network called TransAttUnet, in which the multi-leve…
Rutgers University（罗格斯大学）；SenseBrain（感知大脑公司）；Shanghai AI Laboratory（上海人工智能实验室）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
Transformer architecture has emerged to be successful in a number of natural language processing tasks. However, its applications to medical vision remain largely unexplored. In this study, we present UTNet, a simple yet powerful hybrid Transformer architecture that integrates self-attention into a convolutional neural network for enhancing medical image segmentation. UTNet applies self-attention modules in both encoder and decoder for capturing long-range dependency at different scales with minimal overhead. To this end, we propose an efficient self-attention mechanism along with relative pos…
Wuhan Institute of Technology（武汉工程大学）；Huazhong University of Science and technology（华中科技大学）
Medical image segmentation plays an essential role in developing computer-assisted diagnosis and therapy systems, yet still faces many challenges. In the past few years, the popular encoder-decoder architectures based on CNNs (e.g., U-Net) have been successfully applied in the task of medical image segmentation. However, due to the locality of convolution operations, they demonstrate limitations in learning global context and long-range spatial relations. Recently, several researchers try to introduce transformers to both the encoder and decoder components with promising results, but the effic…
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
Shanghai Jiao Tong University（上海交通大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；SKL-IOTSC, CIS, University of Macau（澳门大学SKL-IOTSC、CIS）；Huazhong University of Science and Technology（华中科技大学）；The Chinese University of Hong Kong（香港中文大学）
Narrowing the semantic gaps in U-Net with learnable skip connections: The case of medical image segmentation
Northeastern University（东北大学）；Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education（教育部医学图像智能计算重点实验室）；DAMO Academy, Alibaba Group（阿里巴巴达摩院）；University of Alberta（阿尔伯塔大学）
CEDRIC - Conservatoire National des Arts et Metiers（国立工艺学院CEDRIC实验室）；Visible Patient SAS（Visible Patient SAS公司）
Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures. In this paper, we introduce the U-Transformer network, which combines a U-shaped architecture for image segmentation with self- and cross-attention from Transformers. U-Transformer overcomes the inability of U-Nets to model long-range contextual interactions and spatial dependencies, which are arguably crucial for accurate segmentation in challenging contexts. To this end, attention mechanisms are incorporated at two main levels: a self-attention module leverages global interactions …
DAE-Former: Dual Attention-guided Efficient Transformer for Medical Image Segmentation
RWTH Aachen University（亚琛工业大学）；Shahid Beheshti University（沙希德·贝赫什提大学）；Iran University of Science and Technology（伊朗科技大学）；University of Regensburg（雷根斯堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusing depth information has been proven effective in this task. The main challenge of this problem is how to aggregate the complementary information from RGB modality and depth modality. However, conventional deep models heavily rely on CNN feature extractors, and the long-range contextual dependencies are usually ignored. In this work, we propose Dual Swin-Transformer based Mutual Interactive Network. We adopt Swin-Transformer as the feature extractor for both RGB and depth modality to model the lo…
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Point cloud completion aims to predict a complete shape in high accuracy from its partial observation. However, previous methods usually suffered from discrete nature of point cloud and unstructured prediction of points in local regions, which makes it hard to reveal fine local geometric details on the complete shape. To resolve this issue, we propose SnowflakeNet with Snowflake Point Deconvolution (SPD) to generate the complete point clouds. The SnowflakeNet models the generation of complete point clouds as the snowflake-like growth of points in 3D space, where the child points are progressiv…
Tsinghua University（清华大学）；Tencent PCG（腾讯平台与内容事业群）；Kuaishou Technology（快手科技）；Wayne State University（韦恩州立大学）
Most existing point cloud completion methods suffer from the discrete nature of point clouds and the unstructured prediction of points in local regions, which makes it difficult to reveal fine local geometric details. To resolve this issue, we propose SnowflakeNet with snowflake point deconvolution (SPD) to generate complete point clouds. SPD models the generation of point clouds as the snowflake-like growth of points, where child points are generated progressively by splitting their parent points after each SPD. Our insight into the detailed geometry is to introduce a skip-transformer in the …
In this paper, we propose a novel network named Vision Transformer for Biomedical Image Segmentation (ViTBIS). Our network splits the input feature maps into three parts with $1\times 1$, $3\times 3$ and $5\times 5$ convolutions in both encoder and decoder. Concat operator is used to merge the features before being fed to three consecutive transformer blocks with attention mechanism embedded inside it. Skip connections are used to connect encoder and decoder transformer blocks. Similarly, transformer blocks and multi scale architecture is used in decoder before being linearly projected to prod…
Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling
Artificial Intelligence School, Anhui University（安徽大学人工智能学院）；National Engineering Laboratory for Robot Visual Perception and Control Technology, College of Electrical and Information Engineering, Hunan University（机器人视觉感知与控制技术国家工程实验室，湖南大学电气与信息工程学院）；Artificial Intelligence School, Xidian University（西安电子科技大学人工智能学院）；Department of Computer Science, The University of Western Australia（西澳大学计算机科学系）；Central Queensland University（中央昆士兰大学）
Iran University of Science and Technology（伊朗科技大学）；RWTH Aachen University（亚琛工业大学）；Shahid Beheshti University（沙希德·贝赫什提大学）；University of Montreal（蒙特利尔大学）；Polytechnique Montreal（蒙特利尔理工学院）；Quebec AI Institute（魁北克人工智能研究所）；University of Regensburg（雷根斯堡大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution operation. Although transformers were first developed to address this issue, they fail to capture low-level features. In contrast, it is demonstrated that both local and global features are crucial for dense prediction, such as segmenting in challenging contexts. In this paper, we propose HiFormer, a novel method that efficiently bridges a CNN and a transformer fo…
Shahid Beheshti University（沙希德·贝赫什提大学）；RWTH Aachen University（亚琛工业大学）；Alzahra University（阿尔扎赫拉大学）；University of Regensburg（雷根斯堡大学）
Melanoma is caused by the abnormal growth of melanocytes in human skin. Like other cancers, this life-threatening skin cancer can be treated with early diagnosis. To support a diagnosis by automatic skin lesion segmentation, several Fully Convolutional Network (FCN) approaches, specifically the U-Net architecture, have been proposed. The U-Net model with a symmetrical architecture has exhibited superior performance in the segmentation task. However, the locality restriction of the convolutional operation incorporated in the U-Net architecture limits its performance in capturing long-range depe…
Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China（人工智能学院，北京师范大学，北京）；Institute of Artificial Intelligence（人工智能研究所）；Future Networks, Beijing Normal University, Zhuhai 519087, China（未来网络，北京师范大学，珠海）
Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious …
Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by learning both global and local features and contextual representations which can be utilized for semantic output prediction by the decoder. Despite their success, the locality of convolutional layers in FCNNs, limits the capability of learning long-range spatial dependencies. Inspired by the recent success of transformers for Natural Language Processing (NLP) in l…
GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction
Department of Computer Science and Engineering, Lehigh University（计算机科学与工程系，莱恩大学）；Department of Civil and Environmental Engineering, Lehigh University（土木与环境工程系，莱恩大学）
Text-guided 3D Human Motion Generation with Keyframe-based Parallel Skip Transformer
School of Electrical, Electronic and Computer Engineering, University of Western Australia（西澳大学电气、电子与计算机工程学院）；University of Melbourne（墨尔本大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织）；Hunan University（湖南大学）；University of Central Florida（中佛罗里达大学）
SKGE-SWIN: End-To-End Autonomous Vehicle Waypoint Prediction and Navigation Using Skip Stage Swin Transformer
Department of Computer Science, Indonesia University of Education（印度尼西亚教育大学计算机科学系）；Research Center for Smart Mechatronics, National Research and Innovation Agency（国家研究与创新局智能机电研究中心）；Department of Computer Science and Electronics, Gadjah Mada University（加查玛达大学计算机科学与电子系）
Camera pose regression methods apply a single forward pass to the query image to estimate the camera pose. As such, they offer a fast and light-weight alternative to traditional localization schemes based on image retrieval. Pose regression approaches simultaneously learn two regression tasks, aiming to jointly estimate the camera position and orientation using a single embedding vector computed by a convolutional backbone. We propose an attention-based approach for pose regression, where the convolutional activation maps are used as sequential inputs. Transformers are applied to encode the se…
In this paper, we present a joint end-to-end line segment detection algorithm using Transformers that is post-processing and heuristics-guided intermediate processing (edge/junction/region detection) free. Our method, named LinE segment TRansformers (LETR), takes advantages of having integrated tokenized queries, a self-attention mechanism, and an encoding-decoding strategy within Transformers by skipping standard heuristic designs for the edge element detection and perceptual grouping processes. We equip Transformers with a multi-scale encoder/decoder strategy to perform fine-grained line seg…
Tel Aviv University（特拉维夫大学）；Facebook AI Research (FAIR)（Facebook AI研究院）
Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a certain classification, existing methods either rely on the obtained attention maps or employ heuristic propagation along the attention graph. In this work, we propose a novel way to compute relevancy for Transformer networks. The method assigns local relevance based on the Deep Taylor Decomposition principle and then propagates these relevancy scores throug…
While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling weight sharing across various token densities. Thus one model offers a range of accuracy and throughput tradeoffs for different applications. Besides, we introduce adaptive token pruning to optimize the patch token sparsity based on the input image. In addition, we investigate knowledge distillation to enhance token selection capability in early transformer…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Texas A&M University（德州农工大学）；Kwai Inc.（快手公司）
Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compress…
Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Sun Yat-sen University（中山大学）；National Supercomputing Center in Shenzhen（国家超级计算深圳中心）；Tsinghua University（清华大学）
University of Science and Technology Beijing（北京科技大学）；Beijing Jiaotong University（北京交通大学）
Image denoising is an important low-level computer vision task, which aims to reconstruct a noise-free and high-quality image from a noisy image. With the development of deep learning, convolutional neural network (CNN) has been gradually applied and achieved great success in image denoising, image compression, image enhancement, etc. Recently, Transformer has been a hot technique, which is widely used to tackle computer vision tasks. However, few Transformer-based methods have been proposed for low-level vision tasks. In this paper, we proposed an image denoising network structure based on Tr…
