mlsanityData to 7 Oct 2026

Efficient Multi-Scale Attention Module with Cross-Spatial Learning

arXiv 2305.13563 ↗First posted 23 May 2023cs.CV cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel dimensionality reduction may bring side effect in extracting deep visual representations. In this paper, a novel efficient multi-scale attention (EMA) module is proposed. Focusing on retaining the information on per channel and decreasing the computational overhead, we reshape the partly channels into the batch dimensions and group the channel dimensions into multiple sub-features which make the spatial semantic features well-distributed inside each feature group. Specifically, apart from encoding the global information to re-calibrate the channel-wise weight in each parallel branch, the output features of the two parallel branches are further aggregated by a cross-dimension interaction for capturing pixel-level pairwise relationship. We conduct extensive ablation studies and experiments on image classification and object detection tasks with popular benchmarks (e.g., CIFAR-100, ImageNet-1k, MS COCO and VisDrone2019) for evaluating its performance.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 23 of its 28 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

23 of 28 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2017Non-local Neural Networkscited by 2,290
  8. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  9. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  10. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  11. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  12. 2019Selective Kernel Networkscited by 401
11 more
  1. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  2. 2016SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioningcited by 219
  3. 2018A2-Nets: Double Attention Networkscited by 136
  4. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  5. 2020Rotate to Attend: Convolutional Triplet Attention Modulecited by 75
  6. 2021SA-Net: Shuffle Attention for Deep Convolutional Neural Networkscited by 54
  7. 2021Polarized Self-Attention: Towards High-quality Pixel-wise Regressioncited by 39
  8. 2019Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networkscited by 33
  9. 2019MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learningcited by 19
  10. 2021Non-deep Networkscited by 14
  11. 2021NAM: Normalization-based Attention Modulecited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 24; 2026: 8.

40 papers.

Sort:

By area:

  1. 2025MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devicescited by 12
  2. 2024SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attentioncited by 9
  3. 2024Enhanced Self-Checkout System for Retail Based on Improved YOLOv10cited by 7
  4. 2024Attention-guided Feature Distillation for Semantic Segmentationcited by 3
  5. 2024SOD-YOLOv8 -- Enhancing YOLOv8 for Small Object Detection in Traffic Scenescited by 3
  6. 2025Advancing Autonomous Vehicle Intelligence: Deep Learning and Multimodal LLM for Traffic Sign Recognition and Robust Lane Detectioncited by 3
  7. 2025Enhancing Layer Attention Efficiency through Pruning Redundant Retrievalscited by 3
  8. 2025An Efficient Aerial Image Detection with Variable Receptive Fieldscited by 2
  9. 2025MRC-DETR: An Adaptive Multi-Residual Coupled Transformer for Bare Board PCB Defect Detectioncited by 2
  10. 2024EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detectioncited by 1
  11. 2025MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone Viewcited by 1
  12. 2025EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgerycited by 1
28 more
  1. 2025Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissectioncited by 1
  2. 2025SDE-DET: A Precision Network for Shatian Pomelo Detection in Complex Orchard Environmentscited by 1
  3. 2025XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Methodcited by 1
  4. 2024Fused attention mechanism-based ore sorting networkcited by 0
  5. 2024RemoCap: Disentangled Representation Learning for Motion Capturecited by 0
  6. 2024Greit-HRNet: Grouped Lightweight High-Resolution Network for Human Pose Estimationcited by 0
  7. 2025A lightweight model FDM-YOLO for small target improvement based on YOLOv8cited by 0
  8. 2025KunlunBaize: LLM with Multi-Scale Convolution and Multi-Token Prediction Under TransformerX Frameworkcited by 0
  9. 2025OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulationcited by 0
  10. 2025SMDDFNet: State-space Modeling and Dynamic Dual Fusion Network for Traffic Sign Detectioncited by 0
  11. 2025A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulationcited by 0
  12. 2025J-DDL: Surface Damage Detection and Localization System for Fighter Aircraftcited by 0
  13. 2025DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detectioncited by 0
  14. 2025Efficient SAR Vessel Detection for FPGA-Based On-Satellite Sensingcited by 0
  15. 2025HGNet: High-Order Spatial Awareness Hypergraph and Multi-Scale Context Attention Network for Colorectal Polyp Detectioncited by 0
  16. 2025A Two-Stage Strategy for Mitosis Detection Using Improved YOLO11x Proposals and ConvNeXt Classificationcited by 0
  17. 2025Vi-SAFE: A Spatial-Temporal Framework for Efficient Violence Detection in Public Surveillancecited by 0
  18. 2025YOLOv11-Litchi: Efficient Litchi Fruit Detection based on UAV-Captured Agricultural Imagery in Complex Orchard Environmentscited by 0
  19. 2025SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understandingcited by 0
  20. 2025A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentationcited by 0
  21. 2026DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Targetcited by 0
  22. 2026SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detectioncited by 0
  23. 2026UniPCB: A Generation-Assisted Vision-Based Measurement Framework for PCB Defect Inspectioncited by 0
  24. 2026CFGPNet: Cross-Attention-Based Fused Gradient Programmed Network Framework for Multispectral Object Detectioncited by 0
  25. 2026ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagerycited by 0
  26. 2026GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detection in CTcited by 0
  27. 2026EMCStereo: Attention-Enhanced Stereo Matching for Thin-Structure Depth Estimation with a Synthetic Tree-Branch Benchmarkcited by 0
  28. 2026LightSleepX: A Lightweight, Inception-Based Dual-Modal Network for Sleep Stagingcited by 0