Competitive Inner-Imaging Squeeze and Excitation for Residual Network

Residual networks, which use a residual unit to supplement the identity mappings, enable very deep convolutional architecture to operate effectively. Moreover, the squeeze-excitation (SE) network proposes an adaptively recalibrating channel-wise attention approach for modeling the relationships of feature maps from different convolutional channels. In this work, we propose a competitive SE mechanism for the residual network. Rescaling the value for each channel in this structure will be determined by the residual and identity mappings jointly, and this design enables us to expand the meaning of channel relationship modeling in residual blocks. Modeling of the competition between residual and identity mappings cause the identity flow to control the complement of the residual feature maps for itself. Furthermore, we design a novel pair-view competitive SE block to shrink the consumption and re-image the global features of intermediate network structure, by using the inner-imaging mechanism, we can model the channel-wise relations with convolution in spatial. We carry out experiments on the CIFAR, SVHN, and ImageNet datasets, and the proposed method can challenge state-of-the-art results.