One-shot Network Pruning at Initialization with Discriminative Image Patches
Yinan Yang (Ritsumeikan University),* Yu Wang (Hitotsubashi University), Ying Ji (Nagoya University), Heng Qi (Dalian University of Technology), Jien Kato (Ritsumeikan University)
The 33rd British Machine Vision Conference
Abstract
One-shot Network Pruning at Initialization (OPaI) is an effective method to decrease network pruning costs. Recently, there is a growing belief that data is unnecessary in OPaI. However, we obtain an opposite conclusion by ablation experiments in two representative OPaI methods, SNIP and GraSP. Specifically, we find that informative data is crucial to enhancing pruning performance. In this paper, we propose two novel methods, Discriminative One-shot Network Pruning (DOP) and Super Stitching, to prune the network by high-level visual discriminative image patches. Our contributions are as follows. (1) Extensive experiments reveal that OPaI is data-dependent. (2) Super Stitching performs significantly better than the original OPaI method on benchmark ImageNet, especially in a highly compressed model.Video
Citation
@inproceedings{Yang_2022_BMVC,
author = {Yinan Yang and Yu Wang and Ying Ji and Heng Qi and Jien Kato},
title = {One-shot Network Pruning at Initialization with Discriminative Image Patches},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0715.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by