luuuyi/CBAM.PyTorch
PyTorch implementation of CBAM (Convolutional Block Attention Module), an attention mechanism that refines CNN feature maps through sequential channel and spatial attention.
Not currently ranked — collecting fresh signals.
star history
This repository provides a non-official PyTorch reimplementation of the CBAM paper from ECCV 2018. CBAM is a plug-and-play attention module that can be integrated into any CNN architecture to adaptively refine intermediate feature maps. The implementation includes channel attention and spatial attention sub-modules applied sequentially at each convolutional block. Results are validated on ImageNet-1K using ResNet50, showing improved top-1 accuracy over baseline.
Frequently asked
- What is luuuyi/CBAM.PyTorch?
- PyTorch implementation of CBAM (Convolutional Block Attention Module), an attention mechanism that refines CNN feature maps through sequential channel and spatial attention.
- Is CBAM.PyTorch open source?
- Yes — luuuyi/CBAM.PyTorch is an open-source project tracked on heatdrop.
- What language is CBAM.PyTorch written in?
- luuuyi/CBAM.PyTorch is primarily written in Python.
- How popular is CBAM.PyTorch?
- luuuyi/CBAM.PyTorch has 1.5k stars on GitHub.
- Where can I find CBAM.PyTorch?
- luuuyi/CBAM.PyTorch is on GitHub at https://github.com/luuuyi/CBAM.PyTorch.