17 set 2019 ano - Low-rank Embedding of Kernels in Convolutional Neural Networks under Random Shuffling (ICASSP 2019)

Descrição:

提出了 randomly-shuffled tensor decompo- sition (RsTD) based convolutional layer

不同于传统的 TD-based compression

shows that the kernel can be embedded into more general or even random low-rank subspaces.

结果：
基于 CIFAR-10 分类任务，RsTD 方法在压缩率jiao低(<0.01) 时，相对传统 TD 方法 ACC 更高。