CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion

TL;DR

This paper introduces CAT, a collaborative attention module that adaptively combines channel and spatial attentions using learned traits, enhancing deep CNN performance across multiple vision tasks.

Contribution

The paper proposes a novel plug-and-play attention module called CAT that models collaboration between channel and spatial attentions with trainable coefficients and introduces a three-way pooling for better feature suppression.

Findings

CAT outperforms existing attention methods on multiple benchmarks.

The adaptive fusion mechanism improves task-specific performance.

Global entropy pooling effectively suppresses noise signals.

Abstract

Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs). Most existing methods focus on one or run them parallel (series), neglecting the collaboration between the two attentions. In order to better establish the feature interaction between the two types of attention, we propose a plug-and-play attention module, which we term "CAT"-activating the Collaboration between spatial and channel Attentions based on learned Traits. Specifically, we represent traits as trainable coefficients (i.e., colla-factors) to adaptively combine contributions of different attention modules to fit different image hierarchies and tasks better. Moreover, we propose the global entropy pooling (GEP) apart from global average pooling (GAP) and global maximum pooling (GMP) operators, an effective component in suppressing noise signals by measuring the information disorder of feature maps. We introduce a three-way pooling operation into attention modules and apply the adaptive mechanism to fuse their outcomes. Extensive experiments on MS COCO, Pascal-VOC, Cifar-100, and ImageNet show that our CAT outperforms existing state-of-the-art attention mechanisms in object detection, instance segmentation, and image classification. The model and code will be released soon.