</> Code with Papers by Syntology

Methods › Computer Vision › Image Model Blocks › CBAM

Convolutional Block Attention Module

CBAM

43 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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.

Given an intermediate feature map 𝐅 ∈ℝ^(C×H×W) as input, CBAM sequentially infers a 1D channel attention map 𝐌_c ∈ℝ^(C×1×1) and a 2D spatial attention map 𝐌ₛ ∈ℝ^(1×H×W). The overall attention process can be summarized as:

𝐅′ = 𝐌_c(𝐅) ⊗𝐅

𝐅″ = 𝐌ₛ(𝐅′) ⊗𝐅′

During multiplication, the attention values are broadcasted (copied) accordingly: channel attention values are broadcasted along the spatial dimension, and vice versa. 𝐅″ is the final refined output.

Source: CBAM: Convolutional Block Attention ModuleSee Code · Jongchan/attention-module

Papers archive 2025-07-28

30 shown of 43, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 60 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Segmentation7
Image Classification6
Semantic Segmentation6
Object Detection5
image-classification5
Diagnostic4
Transfer Learning4
Computational Efficiency3
Management3
Anatomy2
Anomaly Detection2
Autonomous Driving2
Classification2
Data Augmentation2
Defect Detection2
Image Segmentation2
Instance Segmentation2
Lesion Segmentation2
Skin Lesion Segmentation2
Small Object Detection2

Usage over time archive 2025-07-28

Papers per year tagged with CBAM: 2018 to 2025, peak 21 21 0 2018: 1 paper 2018 2019: 0 papers 2019 2020: 0 papers 2020 2021: 2 papers 2021 2022: 7 papers 2022 2023: 5 papers 2023 2024: 21 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (43 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Image Model Blocks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections