AutoDFP: Automatic Data-Free Pruning via Channel Similarity Reconstruction

arXiv:2403.08204v1 Announce Type: new
Abstract: Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods rely on training datasets to fine-tune the compressed model, resulting in high computational burdens and being inapplicable for scenarios with stringent requirements on privacy and security. As an alternative, some data-free methods have been proposed, however, these methods often require handcraft parameter tuning and can only achieve inflexible reconstruction. …

abstract arxiv bridge computational cs.cv cs.lg current data datasets free gap hardware massive networks neural networks pruning resources scale training training datasets type via