jul 10, 2018 - Wide Compression: Tensor Ring Nets (CVPR 2018)
Description:
Three-component decompositionTensor Ring Nets (TRN), in
which layers of a deep neural network are compressed using tensor ring factorization.
结果：
TR-Nets approach is able to compress LeNet-5 by 11× without losing accuracy, and can compress the state-of-the-art Wide ResNet by 243× with only 2.3% degradation in Cifar10 image classification
Added to timeline:
Date:
jul 10, 2018
Now
~ 7 years and 3 months ago