{"url":"/method/cbam","slug":"cbam","name":"CBAM","full_name":"Convolutional Block Attention Module","full_name_withheld":false,"description_markdown":"**Convolutional Block Attention Module (CBAM)** is an attention module for convolutional neural networks. Given an intermediate feature map, the module sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement.\r\n\r\nGiven an intermediate feature map $\\mathbf{F} \\in \\mathbb{R}^{C×H×W}$ as input, CBAM sequentially infers a 1D channel attention map $\\mathbf{M}\\_{c} \\in \\mathbb{R}^{C×1×1}$ and a 2D spatial attention map $\\mathbf{M}\\_{s} \\in \\mathbb{R}^{1×H×W}$. The overall attention process can be summarized as:\r\n\r\n$$ \\mathbf{F}' = \\mathbf{M}\\_{c}\\left(\\mathbf{F}\\right) \\otimes \\mathbf{F} $$\r\n\r\n$$ \\mathbf{F}'' = \\mathbf{M}\\_{s}\\left(\\mathbf{F'}\\right) \\otimes \\mathbf{F'} $$\r\n\r\nDuring multiplication, the attention values are broadcasted (copied) accordingly: channel attention values are broadcasted along the spatial dimension, and vice versa. $\\mathbf{F}''$ is the final refined\r\noutput.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1807.06521v2","title":"CBAM: Convolutional Block Attention Module","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/Jongchan/attention-module/blob/c06383c514ab0032d044cc6fcd8c8207ea222ea7/MODELS/cbam.py#L84","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Model Blocks","url":"/methods/category/image-model-blocks","pwc_aliases":[]}],"n_papers_tagged":43,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Improvement Strategies for Few-Shot Learning in OCT Image Classification of Rare Retinal Diseases","date":"2025-05-26","arxiv_id":"2505.20149","n_code_links":0,"syntology":null},{"paper":"/paper/dual-attention-residual-u-net-for-accurate","title":"Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection","date":"2025-05-23","arxiv_id":"2505.17683","n_code_links":1,"syntology":null},{"paper":"/paper/enhanced-scannet-with-cbam-and-dice-loss-for","title":"Enhanced SCanNet with CBAM and Dice Loss for Semantic Change Detection","date":"2025-05-07","arxiv_id":"2505.04199","n_code_links":1,"syntology":null},{"paper":null,"title":"Intelligent road crack detection and analysis based on improved YOLOv8","date":"2025-04-16","arxiv_id":"2504.13208","n_code_links":0,"syntology":null},{"paper":null,"title":"Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach","date":"2025-03-28","arxiv_id":"2503.22251","n_code_links":0,"syntology":null},{"paper":"/paper/an-attention-guided-deep-learning-approach","title":"An Attention-Guided Deep Learning Approach for Classifying 39 Skin Lesion Types","date":"2025-01-10","arxiv_id":"2501.05991","n_code_links":1,"syntology":null},{"paper":null,"title":"AI-Powered Cow Detection in Complex Farm Environments","date":"2025-01-03","arxiv_id":"2501.02080","n_code_links":0,"syntology":null},{"paper":null,"title":"Research on vehicle detection based on improved YOLOv8 network","date":"2024-12-31","arxiv_id":"2501.00300","n_code_links":0,"syntology":null},{"paper":"/paper/hybrid-attention-network-an-efficient","title":"HYATT-Net is Grand: A Hybrid Attention Network for Performant Anatomical Landmark Detection","date":"2024-12-09","arxiv_id":"2412.06499","n_code_links":1,"syntology":null},{"paper":null,"title":"Integrating YOLO11 and Convolution Block Attention Module for Multi-Season Segmentation of Tree Trunks and Branches in Commercial Apple Orchards","date":"2024-12-07","arxiv_id":"2412.05728","n_code_links":0,"syntology":null},{"paper":null,"title":"An Explainable Attention Model for Cervical Precancer Risk Classification using Colposcopic Images","date":"2024-11-14","arxiv_id":"2411.09469","n_code_links":0,"syntology":null},{"paper":null,"title":"Breast Cancer Histopathology Classification using CBAM-EfficientNetV2 with Transfer Learning","date":"2024-10-29","arxiv_id":"2410.22392","n_code_links":0,"syntology":null},{"paper":"/paper/hyperspectral-imaging-based-perception-in","title":"Hyperspectral Imaging-Based Perception in Autonomous Driving Scenarios: Benchmarking Baseline Semantic Segmentation Models","date":"2024-10-29","arxiv_id":"2410.22101","n_code_links":1,"syntology":null},{"paper":null,"title":"Emotion Recognition with Facial Attention and Objective Activation Functions","date":"2024-10-23","arxiv_id":"2410.17740","n_code_links":0,"syntology":null},{"paper":null,"title":"A Novel Method for Accurate & Real-time Food Classification: The Synergistic Integration of EfficientNetB7, CBAM, Transfer Learning, and Data Augmentation","date":"2024-10-03","arxiv_id":"2410.02304","n_code_links":0,"syntology":null},{"paper":null,"title":"CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement","date":"2024-09-30","arxiv_id":"2409.20113","n_code_links":0,"syntology":null},{"paper":"/paper/a-lightweight-insulator-defect-detection","title":"A Lightweight Insulator Defect Detection Model Based on Drone Images","date":"2024-08-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Research on Improved U-net Based Remote Sensing Image Segmentation Algorithm","date":"2024-08-22","arxiv_id":"2408.12672","n_code_links":0,"syntology":null},{"paper":null,"title":"An Explainable Non-local Network for COVID-19 Diagnosis","date":"2024-08-08","arxiv_id":"2408.04300","n_code_links":0,"syntology":null},{"paper":null,"title":"Attention is all you need for an improved CNN-based flash flood susceptibility modeling. The case of the ungauged Rheraya watershed, Morocco","date":"2024-08-03","arxiv_id":"2408.02692","n_code_links":0,"syntology":null},{"paper":null,"title":"SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes","date":"2024-08-02","arxiv_id":"2408.08879","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery","date":"2024-07-27","arxiv_id":"2407.19184","n_code_links":0,"syntology":null},{"paper":"/paper/pick-or-mix-dynamic-channel-sampling-for-1","title":"Pick-or-Mix: Dynamic Channel Sampling for ConvNets","date":"2024-06-16","arxiv_id":"2406.10935","n_code_links":1,"syntology":null},{"paper":"/paper/ac-mambaseg-an-adaptive-convolution-and-mamba","title":"AC-MAMBASEG: An adaptive convolution and Mamba-based architecture for enhanced skin lesion segmentation","date":"2024-05-05","arxiv_id":"2405.03011","n_code_links":1,"syntology":null},{"paper":null,"title":"A Novel Approach to Chest X-ray Lung Segmentation Using U-net and Modified Convolutional Block Attention Module","date":"2024-04-22","arxiv_id":"2404.14322","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Ship Classification in Optical Satellite Imagery: Integrating Convolutional Block Attention Module with ResNet for Improved Performance","date":"2024-04-02","arxiv_id":"2404.02135","n_code_links":0,"syntology":null},{"paper":"/paper/yolov8-am-yolov8-with-attention-mechanisms","title":"YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection","date":"2024-02-14","arxiv_id":"2402.09329","n_code_links":1,"syntology":null},{"paper":null,"title":"Attention Modules Improve Modern Image-Level Anomaly Detection: A DifferNet Case Study","date":"2024-01-13","arxiv_id":"2401.08686","n_code_links":0,"syntology":null},{"paper":"/paper/hic-yolov5-improved-yolov5-for-small-object","title":"HIC-YOLOv5: Improved YOLOv5 For Small Object Detection","date":"2023-09-28","arxiv_id":"2309.16393","n_code_links":1,"syntology":null},{"paper":null,"title":"Marine Debris Detection in Satellite Surveillance using Attention Mechanisms","date":"2023-07-09","arxiv_id":"2307.04128","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/segmentation","name":"Segmentation","papers":7},{"task":"/task/image-classification","name":"Image Classification","papers":6},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":6},{"task":"/task/object-detection","name":"Object Detection","papers":5},{"task":"/task/image-classification","name":"image-classification","papers":5},{"task":"/task/diagnostic","name":"Diagnostic","papers":4},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":4},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":3},{"task":"/task/management","name":"Management","papers":3},{"task":"/task/anatomy","name":"Anatomy","papers":2},{"task":"/task/anomaly-detection","name":"Anomaly Detection","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/classification-1","name":"Classification","papers":2},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":2},{"task":"/task/defect-detection","name":"Defect Detection","papers":2},{"task":"/task/image-segmentation","name":"Image Segmentation","papers":2},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":2},{"task":"/task/lesion-segmentation","name":"Lesion Segmentation","papers":2},{"task":"/task/skin-lesion-segmentation","name":"Skin Lesion Segmentation","papers":2},{"task":"/task/small-object-detection","name":"Small Object Detection","papers":2}],"tasks_shown":20,"n_tasks":60,"usage_by_year":[{"year":"2018","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":7},{"year":"2023","papers":5},{"year":"2024","papers":21},{"year":"2025","papers":7}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/cbam"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}