English

Boosting Pruned Networks with Linear Over-parameterization

Computer Vision and Pattern Recognition 2024-01-01 v3

Abstract

Structured pruning compresses neural networks by reducing channels (filters) for fast inference and low footprint at run-time. To restore accuracy after pruning, fine-tuning is usually applied to pruned networks. However, too few remaining parameters in pruned networks inevitably bring a great challenge to fine-tuning to restore accuracy. To address this challenge, we propose a novel method that first linearly over-parameterizes the compact layers in pruned networks to enlarge the number of fine-tuning parameters and then re-parameterizes them to the original layers after fine-tuning. Specifically, we equivalently expand the convolution/linear layer with several consecutive convolution/linear layers that do not alter the current output feature maps. Furthermore, we utilize similarity-preserving knowledge distillation that encourages the over-parameterized block to learn the immediate data-to-data similarities of the corresponding dense layer to maintain its feature learning ability. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet which significantly outperforms the vanilla fine-tuning strategy, especially for large pruning ratio.

Keywords

Cite

@article{arxiv.2204.11444,
  title  = {Boosting Pruned Networks with Linear Over-parameterization},
  author = {Yu Qian and Jian Cao and Xiaoshuang Li and Jie Zhang and Hufei Li and Jue Chen},
  journal= {arXiv preprint arXiv:2204.11444},
  year   = {2024}
}
R2 v1 2026-06-24T10:57:23.233Z