2 papers
cs.CV2019
Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks
Zhonghui You, Kun Yan, Jinmian Ye +2
Filter pruning is one of the most effective ways to accelerate and compress convolutional neural networks (CNNs). In this work, we propose a global filter pruning algorithm called…
cs.CV2018
Adversarial Noise Layer: Regularize Neural Network By Adding Noise
Zhonghui You, Jinmian Ye, Kunming Li +2
In this paper, we introduce a novel regularization method called Adversarial Noise Layer (ANL) and its efficient version called Class Adversarial Noise Layer (CANL), which are able…