Filter pruning via schatten p-norm

Yixiang Lin; Jintang Bian; Jianhuang Lai; Xiaohua Xie

doi:10.1117/12.3021622

25 March 2024 Filter pruning via schatten p-norm

Yixiang Lin, Jintang Bian, Jianhuang Lai, Xiaohua Xie

Proceedings Volume 13089, Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023); 1308914 (2024) https://doi.org/10.1117/12.3021622
Event: Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023), 2023, Suzhou, China

Abstract

Filter pruning is a widely employed model compression technique, with the inter-channel method currently recognized as the most efficient approach for filter pruning. However, existing inter-channel methods have not fully explored the independence between convolutional channels. In this paper, we propose to use the Schatten p-norm to extract rank information between convolutional channels and measure the importance of a specific channel by analyzing the change in rank information after its removal. The principle underlying our pruning approach is that a smaller change in rank information corresponds to a lesser degree of importance for the channel. Besides, to reduce the computation time required for calculating channel importance, we propose employing a prototype-based approach. We have verified the effectiveness and efficiency of our proposed method on various datasets and models. As an example, when applying our approach to ResNet-56, we achieved an accuracy improvement of 0.91% while the model size and FLOPs were reduced by 42.8% and 47.4% respectively on the CIFAR10 dataset.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yixiang Lin, Jintang Bian, Jianhuang Lai, and Xiaohua Xie "Filter pruning via schatten p-norm", Proc. SPIE 13089, Fifteenth International Conference on Graphics and Image Processing (ICGIP 2023), 1308914 (25 March 2024); https://doi.org/10.1117/12.3021622

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available