The Bjorck and Pereyra algorithms used for solving Vandermonde systemof equation are modified for the case where the points are symmetricly situated aroundzero. The working operation is saved about half. A forward err...The Bjorck and Pereyra algorithms used for solving Vandermonde systemof equation are modified for the case where the points are symmetricly situated aroundzero. The working operation is saved about half. A forward error analysis is presentedfor the modified algorithms, and it's shown that if the points are situated in some order,the error bound are as good as Higham's result in 1987.展开更多
文摘针对基于互学习的知识蒸馏方法中存在模型只关注教师网络和学生网络的分布差异,而没有考虑其他的约束条件,只关注了结果导向的监督,而缺少过程导向监督的不足,提出了一种拓扑一致性指导的对抗互学习知识蒸馏方法(Topology-guided adversarial deep mutual learning,TADML).该方法将教师网络和学生网络同时训练,网络之间相互指导学习,不仅采用网络输出的类分布之间的差异,还设计了网络中间特征的拓扑性差异度量.训练过程采用对抗训练,进一步提高教师网络和学生网络的判别性.在分类数据集CIFAR10、CIFAR100和Tiny-ImageNet及行人重识别数据集Market1501上的实验结果表明了TADML的有效性,TADML取得了同类模型压缩方法中最好的效果.
基金Supported by National Natural Science Foundation of China,under Grant Number 60175008.and Natural Science Foundation of Fujian Province under Grant A0110004.
文摘The Bjorck and Pereyra algorithms used for solving Vandermonde systemof equation are modified for the case where the points are symmetricly situated aroundzero. The working operation is saved about half. A forward error analysis is presentedfor the modified algorithms, and it's shown that if the points are situated in some order,the error bound are as good as Higham's result in 1987.