Multi-Scale Attention

Ask about this topic

Overview

Multi-scale attention studies how models can combine fine-grained features with broader context across image regions, feature-pyramid levels, or time windows. Common approaches include hierarchical and window-based attention, cross-scale feature fusion, and efficient linear attention that allocates computation across resolutions. These methods are used in tasks such as object detection and segmentation on benchmarks like COCO and ADE20K, as well as time-series forecasting and sequence modeling. A central challenge is aligning useful information across scales while controlling computation, and gains must be tested across varied datasets and settings.

Latest papers

CardsList

39 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.

  1. Revisiting Cross-Attention Mechanisms: Leveraging Beneficial Noise for Domain-Adaptive Learning

    Mar 18, 2026Zelin Zang, Yehui Yang, Fei Wang +2Unsupervised Domain AdaptationAttention Mechanisms

    School of Engineering, Westlake University, Hangzhou, China · Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences (HKISI-CAS), Hong Kong, China · State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China +2

  2. RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images

    Mar 12, 2026Bin Wan, Runmin Cong, Xiaofei Zhou +3Salient Object DetectionMulti-Scale Attention

    School of Control Science and Engineering, Shandong University, Jinan 250061, China · Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250061, China · School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China +2

  3. Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling

    Mar 4, 2026Wenguang Tao, Xiaotian Wang, Tian Yan +2Long-Range Dependency ModelingSmall Object Detection

    Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China · Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China

  4. ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

    Mar 3, 2026Chun-Wun Cheng, Yanqi Cheng, Peiyuan Jing +4U-NetMedical Image Segmentation

    Department of Applied Mathematics and Theoretical Physics, University of Cambridge, UK · School of Engineering, Zurich University of Applied Sciences, CH · Bioengineering Department and ImperialX, Imperial College London, UK +2

  5. Small Object Detection Model with Spatial Laplacian Pyramid Attention and Multi-Scale Features Enhancement in Aerial Images

    Feb 26, 2026Zhangjian Ji, Huijia Yan, Shaotong Qiao +2Small Object DetectionRemote Sensing Small Object Detection

    Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China

  6. Position-Aware Sequential Attention for Accurate Next Item Recommendations

    Feb 24, 2026Timur Nabiev, Evgeny FrolovAttention MechanismsSequential Recommendation

    Skolkovo Institute of Science and Technology · AIRI

  7. Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks

    Feb 22, 2026Sushi Rao, Jingwei LiImage Super-ResolutionMulti-Scale Attention

    Zhejiang Gongshang University

  8. Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impaired

    Feb 18, 2026Qi He, XiangXiang Wang, Jingtao Zhang +5Visually Impaired Navigation Assistance3D Scene Completion

    School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China. · Sichuan Provincial Key Laboratory for Human Disease Gene Study, Sichuan Academy of Medical Sciences & Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, Sichuan, China. · Tibetan Language Intelligence National Key Laboratory, Qinghai Normal University, Xining, Qinghai, China. +2

  9. Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images

    Dec 3, 2024Xiangyong Lu, Masanori Suganuma, Takayuki OkataniHybrid CNN-Transformer ArchitecturesObject Pose Estimation

    Graduate School of Information Sciences, Tohoku University. · RIKEN Center for AIP