CBAM: Convolutional Block Attention Module

Code

• github.com/xmu-xiaoma666/External-Attention-pytorch
  pytorch★ 12,169
• github.com/osmr/imgclsmob
  mxnet★ 3,015
• github.com/e96031413/AA-YOLO
  pytorch★ 9
• github.com/e96031413/PyTorch_YOLOv4-tiny
  pytorch★ 9
• github.com/jihoojo03/UNet-CBAM_Keras
  none★ 5
• github.com/kishanAk21/Skin-Cancer-Image-Classification
  none★ 0
• github.com/laugh12321/3D-Attention-Keras
  tf★ 0
• github.com/2024-MindSpore-1/Code7/tree/main/CBAM
  mindspore★ 0
• github.com/gan3sh500/custom-pooling
  pytorch★ 0
• github.com/Nithesh5/torch-adni-bagging-with-attentional
  pytorch★ 0

Abstract

We propose Convolutional Block Attention Module (CBAM), a simple yet effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our 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. Because CBAM is a lightweight and general module, it can be integrated into any CNN architectures seamlessly with negligible overheads and is end-to-end trainable along with base CNNs. We validate our CBAM through extensive experiments on ImageNet-1K, MS~COCO detection, and VOC~2007 detection datasets. Our experiments show consistent improvements in classification and detection performances with various models, demonstrating the wide applicability of CBAM. The code and models will be publicly available.

Tasks

Benchmark Results

Reproductions