Abstract Channel-Spatial mixed attention methods have been proven to enhance the representation capability of convolutional neural networks. Most existing channel-spatial mixed attention methods decouple the channel domain and spatial domain, investing different orders of computational complexity in calculating attention for the two domains. However, both the channel domain and spatial domain are equally important and deserve comparable levels of complexity in attention computation. To solve this problem, we propose a novel channel-spatial mixed attention method, which is called D ual-domain B alanced C hannel- S patial M ixed A ttention (DBCSMA). The input tensor is first decomposed into channel and spatial domains using global pooling. Then, the same order of complexity is dedicated to calculating attention in both the channel domain and the spatial domain, and a mixed attention tensor is generated using multiplicative aggregation. Finally, input channel information and spatial information are simultaneously recalibrated using multiplication of this mixed attention tensor and the input tensor. Experimental results demonstrate that DBCSMA achieves superior performance compared to most existing channel-spatial mixed attention methods while using lower complexity.
Zhu et al. (Wed,) studied this question.