One-shot Network Pruning at Initialization with Discriminative Image Patches

13 Sep 2022  ·  Yinan Yang, Yu Wang, Ying Ji, Heng Qi, Jien Kato ·

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.

PDF Abstract
No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.