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.
翻译:残余网络使用残余单元来补充身份绘图,使非常深层的革命结构能够有效运作。此外,挤压-勘探(SE)网络提出一个适应性再校准渠道关注方法,以模拟不同革命渠道的地貌图关系。在这项工作中,我们提议为残余网络建立一个竞争性的SE机制。调整这一结构中每个渠道的价值将由残余和身份绘图共同确定,这一设计使我们能够扩大剩余区块的频道关系模型的含义。对残余和身份绘图之间的竞争进行建模,从而控制剩余地貌图的补充。此外,我们设计了一个新型双视图竞争性SE区块,通过内成形机制缩小和重新塑造中间网络结构的全球特征。我们可以模拟与空间革命的频道关系。我们在CIFAR、SVHN和图像网络数据集上进行实验,拟议的方法可以挑战最新结果。