CBAM: Convolutional Block Attention Module
This addresses the need for better feature refinement in CNNs for computer vision tasks, offering a general and efficient solution with broad applicability.
The paper tackled the problem of improving convolutional neural networks by proposing CBAM, a lightweight attention module that refines features along channel and spatial dimensions, resulting in consistent performance gains on ImageNet-1K, MS COCO, and VOC 2007 datasets.
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.