In recent years, the connections between deep residual networks and first-order Ordinary Differential Equations (ODEs) have been disclosed. In this work, we further bridge the deep neural architecture design with the second-order ODEs and propose a novel reversible neural network, termed as m-RevNet, that is characterized by inserting momentum update to residual blocks. The reversible property allows us to perform backward pass without access to activation values of the forward pass, greatly relieving the storage burden during training. Furthermore, the theoretical foundation based on second-order ODEs grants m-RevNet with stronger representational power than vanilla residual networks, which potentially explains its performance gains. For certain learning scenarios, we analytically and empirically reveal that our m-RevNet succeeds while standard ResNet fails. Comprehensive experiments on various image classification and semantic segmentation benchmarks demonstrate the superiority of our m-RevNet over ResNet, concerning both memory efficiency and recognition performance.
翻译:近年来,深残余网络和一阶普通等同(ODEs)之间的联系已经披露。在这项工作中,我们进一步将深神经结构设计与二阶数字交换,并提议一个新的可逆神经网络,称为M-RevNet,其特点是将动力更新插入剩余区块。可逆财产使我们能够在无法激活远端通道价值的情况下进行后退飞行,大大减轻了培训期间的存储负担。此外,基于二阶数字交换所的理论基础授予M-RevNet比香草剩余网络更强的表达力,这有可能解释其绩效收益。对于某些学习情景,我们从分析和经验上表明,我们的M-RevNet在标准ResNet失败时成功。关于各种图像分类和语义分割基准的全面实验表明,我们的M-RevNet在记忆效率和认知性表现方面优于ResNet。