Model Compression via Hyper-Structure Network

Shangqian Gao, Feihu Huang, Heng Huang

Abstract: In this paper, we propose a novel channel pruning method to solve the problem of compression and acceleration of Convolutional Neural Networks (CNNs). Previous channel pruning methods usually ignore the relationships between channels and layers. Many of them parameterize each channel independently by using gates or similar concepts. To fill this gap, a hyper-structure network is proposed to generate the architecture of the main network. Like the existing hypernet, our hyper-structure network can be optimized by regular backpropagation. Moreover, we use a regularization term to specify the computational resource of the compact network. Usually, FLOPs is used as the criterion of computational resource. However, if FLOPs is used in the regularization, it may over penalize early layers. To address this issue, we further introduce learnable layer-wise scaling factors to balance the gradients from different terms, and they can be optimized by hyper-gradient descent. Extensive experimental results on CIFAR-10 and ImageNet show that our method is competitive with state-of-the-art methods.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ZKueVyaSVn