CBAM: Convolutional Block Attention Module

TL;DR

CBAM introduces a lightweight attention module for CNNs that enhances feature refinement by sequentially inferring channel and spatial attention maps, leading to improved performance across multiple vision tasks.

Contribution

It presents a novel, efficient attention module that can be integrated into any CNN to improve feature representation and task performance.

Findings

Consistent performance improvements on ImageNet-1K classification.

Enhanced detection accuracy on MS COCO and VOC datasets.

Lightweight design with negligible computational overhead.

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.