Competitive Inner-Imaging Squeeze and Excitation for Residual Network

Residual Network make the very deep convolutional architecture works well, which use the residual unit to supplement the identity mappings. On the other hand, Squeeze-Excitation (SE) network propose a adaptively recalibrates channel-wise attention approach to model the relationship of feature maps from different convolutional channel. In this work, we propose the competitive SE mechanism for residual network, rescaling value for each channel in this structure will be determined by residual and identity mappings jointly, this design enables us to expand the meaning of channel relationship modeling in residual blocks: the modeling of competition between residual and identity mappings make identity flow can controll the complement of residual feature maps for itself. Further, we design a novel pair-view competitive SE block to shrink the consumption and re-image the global characterizations of intermediate convolutional channels. We carried out experiments on datasets: CIFAR, SVHN, ImageNet, the proposed method can be compare with the state-of-the-art results.