# SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

arXiv: https://arxiv.org/abs/1806.05320 · HTML: https://mlsanity.com/paper/1806.05320/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classification](https://mlsanity.com/paper/2203.15751/) (2022)
- [Homological Neural Networks: A Sparse Architecture for Multivariate Complexity](https://mlsanity.com/paper/2306.15337/) (2023)
- [Filter Pruning based on Information Capacity and Independence](https://mlsanity.com/paper/2303.03645/) (2023)
- [Self Similarity Matrix based CNN Filter Pruning](https://mlsanity.com/paper/2211.01814/) (2022)
- [D-Score: A Synapse-Inspired Approach for Filter Pruning](https://mlsanity.com/paper/2308.04470/) (2023)
- [Compressive Feature Selection for Remote Visual Multi-Task Inference](https://mlsanity.com/paper/2405.09077/) (2024)

## Abstract (arXiv)

Deep Convolutional Neural Networks (CNN) has achieved significant success in computer vision field. However, the high computational cost of the deep complex models prevents the deployment on edge devices with limited memory and computational resource. In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP). We first apply spectral clustering on filters layer by layer to explore their intrinsic connections and only count on efficient groups. By self-adaption manners, the pruning operations can be done in few epochs to let the network gradually choose meaningful groups. According to this strategy, we not only achieve model compression while keeping considerable performance, but also find a novel angle to interpret the model compression process.