SGAD：软引导自适应丢弃神经网络
SGAD: Soft-Guided Adaptively-Dropped Neural Network
摘要：
深度神经网络（DNN）已被证明具有许多冗余。因此，已经做出了许多努力来压缩DNN。然而，现有的模型压缩方法对所有输入样本都是平等对待的，而忽略了不同输入样本被正确分类的难度是不同的这一事实。为了解决这个问题，在这项工作中，DNN与自适应丢弃机制进行了很好的探索。为了告知DNN输入样本的分类难度，引入了包含输入样本信息的指南以提高性能。在此基础上，提出了一种新的软引导自适应丢弃（soft-guided adaptively-dropped，SGAD）神经网络。与32层残差神经网络相比，SGAD在CIFAR-10上的精度下降不到1%，而FLOPs降低了77%。
英文摘要：
Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different. To address this problem, DNNs with adaptive dropping mechanism are well explored in this work. To inform the DNNs how difficult the input samples can be classified, a guideline that contains the information of input samples is introduced to improve the performance. Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper. Compared with the 32 layers residual neural networks, the presented SGAD can reduce the FLOPs by 77% with less than 1% drop in accuracy on CIFAR-10.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
