pytorch / pytorch/vision

Adding CBAM operator

Open
#8,212 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
17.9k
Forks
7.3k
Avg merge
1d 15h
Merged PRs (30d)
13

Description

🚀 The feature

Implement CBAM (Convolutional Block Attention Module). It is an attention operator released in 2018 (paper), similar to Squeeze and Excitation but with the addition of spatial attention.

Motivation, pitch

In some cases, CBAM presents better results than SE due to the addition of spatial attention. SE uses only global channel-wise attention (each channel is scaled by the same value), while CBAM computes an attention map for each channel, scaling "by regions", learning more granular attention.

Alternatives

No response

Additional context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the linked CBAM paper and compare its channel and spatial attention design with the repository's existing Squeeze-and-Excitation support. Identify the appropriate model entry point and establish that the implementation matches the paper's behavior before considering the work done.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.