mlsanityData to 7 Oct 2026

Global Attention Mechanism: Retain Information to Enhance Channel-Spatial Interactions

arXiv 2112.05561 ↗First posted 10 Dec 2021cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

A variety of attention mechanisms have been studied to improve the performance of various computer vision tasks. However, the prior methods overlooked the significance of retaining the information on both channel and spatial aspects to enhance the cross-dimension interactions. Therefore, we propose a global attention mechanism that boosts the performance of deep neural networks by reducing information reduction and magnifying the global interactive representations. We introduce 3D-permutation with multilayer-perceptron for channel attention alongside a convolutional spatial attention submodule. The evaluation of the proposed mechanism for the image classification task on CIFAR-100 and ImageNet-1K indicates that our method stably outperforms several recent attention mechanisms with both ResNet and lightweight MobileNet.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 10 Dec 2021.

Builds on

12 of 18 references.

References · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  7. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  8. 2021Scaling Vision Transformerscited by 993
  9. 2017Residual Attention Network for Image Classificationcited by 385
  10. 2018BAM: Bottleneck Attention Modulecited by 171
  11. 2018Attention Branch Network: Learning of Attention Mechanism for Visual Explanationcited by 108
  12. 2020Rotate to Attend: Convolutional Triplet Attention Modulecited by 75

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 13; 2025: 11; 2026: 6.

39 papers.

Sort:

By area:

  1. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  2. 2025DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokenscited by 21
  3. 2023Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithmcited by 12
  4. 2023RFAConv: Receptive-Field Attention Convolution for Improving Convolutional Neural Networkscited by 10
  5. 2024YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Imagescited by 10
  6. 2024BRAU-Net++: U-Shaped Hybrid CNN-Transformer Network for Medical Image Segmentationcited by 7
  7. 2024YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detectioncited by 7
  8. 2024LoCI-DiffCom: Longitudinal Consistency-Informed Diffusion Model for 3D Infant Brain Image Completioncited by 6
  9. 2025DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Accelerationcited by 5
  10. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
  11. 2025RaLiFlow: Scene Flow Estimation with 4D Radar and LiDAR Point Cloudscited by 3
  12. 2023DeepLOC: Deep Learning-based Bone Pathology Localization and Classification in Wrist X-ray Imagescited by 2
27 more
  1. 2023Underwater target detection based on improved YOLOv7cited by 1
  2. 2023Dynamic Graph Convolutional Network with Attention Fusion for Traffic Flow Predictioncited by 1
  3. 2024YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5cited by 1
  4. 2024Global Context Modeling in YOLOv8 for Pediatric Wrist Fracture Detectioncited by 1
  5. 2024Pediatric Wrist Fracture Detection Using Feature Context Excitation Modules in X-ray Imagescited by 1
  6. 2025Cott-ADNet: Lightweight Real-Time Cotton Boll and Flower Detection Under Field Conditionscited by 1
  7. 2022Semantic Interleaving Global Channel Attention for Multilabel Remote Sensing Image Classificationcited by 0
  8. 2022Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in Complex Fire Scenarioscited by 0
  9. 2022Finger Multimodal Feature Fusion and Recognition Based on Channel Spatial Attentioncited by 0
  10. 2023Two-Stage Adaptive Network for Semi-Supervised Cross-Domain Crater Detection under Varying Scenario Distributionscited by 0
  11. 2024EncodeNet: A Framework for Boosting DNN Accuracy with Entropy-driven Generalized Converting Autoencodercited by 0
  12. 2024GAN-HA: A generative adversarial network with a novel heterogeneous dual-discriminator network and a new attention-based fusion strategy for infrared and visible image fusioncited by 0
  13. 2024GSO-YOLO: Global Stability Optimization YOLO for Construction Site Detectioncited by 0
  14. 2024Bi-temporal Gaussian Feature Dependency Guided Change Detection in Remote Sensing Imagescited by 0
  15. 2024Improving Generalization Performance of YOLOv8 for Camera Trap Object Detectioncited by 0
  16. 2025Improved YOLOv7x-Based Defect Detection Algorithm for Power Equipmentcited by 0
  17. 2025DMAGaze: Gaze Estimation Based on Feature Disentanglement and Multi-Scale Attentioncited by 0
  18. 2025Document Image Rectification Bases on Self-Adaptive Multitask Fusioncited by 0
  19. 2025FPDANet: A Multi-Section Classification Model for Intelligent Screening of Fetal Ultrasoundcited by 0
  20. 2025Hybrid Swin Attention Networks for Simultaneously Low-Dose PET and CT Denoisingcited by 0
  21. 2025HiPerformer: A High-Performance Global-Local Segmentation Model with Modular Hierarchical Fusion Strategycited by 0
  22. 2026Mask-Guided Multi-Task Network for Face Attribute Recognitioncited by 0
  23. 2026Boundary and Position Information Mining for Aerial Small Object Detectioncited by 0
  24. 2026GDA-YOLO11: Amodal Instance Segmentation for Occlusion-Robust Robotic Fruit Harvestingcited by 0
  25. 2026SMR-Net:Robot Snap Detection Based on Multi-Scale Features and Self-Attention Networkcited by 0
  26. 2026Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimationcited by 0
  27. 2026YOLO-AMC: An Improved YOLO Architecture with Attention Mechanisms for Building Crack Detectioncited by 0