# REPrune: Filter Pruning via Representative Election

arXiv: https://arxiv.org/abs/2007.06932 · HTML: https://mlsanity.com/paper/2007.06932/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 3 of 3)

- [A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification](https://mlsanity.com/paper/2203.15751/) (2022)
- [Efficient Similarity-based Passive Filter Pruning for Compressing CNNs](https://mlsanity.com/paper/2210.17416/) (2022)
- [Compressing audio CNNs with graph centrality based filter pruning](https://mlsanity.com/paper/2305.03391/) (2023)

## Abstract (arXiv)

Even though norm-based filter pruning methods are widely accepted, it is questionable whether the "smaller-norm-less-important" criterion is optimal in determining filters to prune. Especially when we can keep only a small fraction of the original filters, it is more crucial to choose the filters that can best represent the whole filters regardless of norm values. Our novel pruning method entitled "REPrune" addresses this problem by selecting representative filters via clustering. By selecting one filter from a cluster of similar filters and avoiding selecting adjacent large filters, REPrune can achieve a better compression rate with similar accuracy. Our method also recovers the accuracy more rapidly and requires a smaller shift of filters during fine-tuning. Empirically, REPrune reduces more than 49% FLOPs, with 0.53% accuracy gain on ResNet-110 for CIFAR-10. Also, REPrune reduces more than 41.8% FLOPs with 1.67% Top-1 validation loss on ResNet-18 for ImageNet.