Residual Networks 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 an 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 carry out experiments on datasets: CIFAR, SVHN, ImageNet, the proposed method can be compared with the state-of-the-art results.
翻译:残余网络使非常深层的革命结构运作良好,利用残余单元来补充身份制图。另一方面,Squeeze-Expurence(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竞争性的SE机制,这一结构中每个频道的调整价值将由残余和身份制图共同确定,这一设计使我们能够扩大剩余区段的频道关系建模的含义:残留和身份制图之间的竞争建模使身份流动能够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SEE区块,以缩小中间革命渠道的消耗量并重新塑造全球特征。我们在数据集上进行实验:CIFAR、SVHN、图像网,建议的方法可以与最新结果进行比较。