# Asymptotic Soft Cluster Pruning for Deep Neural Networks

arXiv: https://arxiv.org/abs/2206.08186 · HTML: https://mlsanity.com/paper/2206.08186/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.06866/) (2018)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures](https://mlsanity.com/paper/1607.03250/) (2016)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression](https://mlsanity.com/paper/2003.08935/) (2020)
- [Neural Networks with Few Multiplications](https://mlsanity.com/paper/1510.03009/) (2015)
- [Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1808.07471/) (2018)
- [Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning](https://mlsanity.com/paper/1901.07827/) (2019)
- [Softer Pruning, Incremental Regularization](https://mlsanity.com/paper/2010.09498/) (2020)

## Abstract (arXiv)

Filter pruning method introduces structural sparsity by removing selected filters and is thus particularly effective for reducing complexity. Previous works empirically prune networks from the point of view that filter with smaller norm contributes less to the final results. However, such criteria has been proven sensitive to the distribution of filters, and the accuracy may hard to recover since the capacity gap is fixed once pruned. In this paper, we propose a novel filter pruning method called Asymptotic Soft Cluster Pruning (ASCP), to identify the redundancy of network based on the similarity of filters. Each filter from over-parameterized network is first distinguished by clustering, and then reconstructed to manually introduce redundancy into it. Several guidelines of clustering are proposed to better preserve feature extraction ability. After reconstruction, filters are allowed to be updated to eliminate the effect caused by mistakenly selected. Besides, various decaying strategies of the pruning rate are adopted to stabilize the pruning process and improve the final performance as well. By gradually generating more identical filters within each cluster, ASCP can remove them through channel addition operation with almost no accuracy drop. Extensive experiments on CIFAR-10 and ImageNet datasets show that our method can achieve competitive results compared with many state-of-the-art algorithms.