# Feature Statistics Guided Efficient Filter Pruning

arXiv: https://arxiv.org/abs/2005.12193 · HTML: https://mlsanity.com/paper/2005.12193/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 11 of 11)

- [Teaching Humans When To Defer to a Classifier via Exemplars](https://mlsanity.com/paper/2111.11297/) (2021)
- [Fair Clustering Using Antidote Data](https://mlsanity.com/paper/2106.00600/) (2021)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [Explanatory machine learning for sequential human teaching](https://mlsanity.com/paper/2205.10250/) (2022)
- [ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN](https://mlsanity.com/paper/2101.06407/) (2021)
- [SMOF: Squeezing More Out of Filters Yields Hardware-Friendly CNN Pruning](https://mlsanity.com/paper/2110.10842/) (2021)
- [Time-Constrained Learning](https://mlsanity.com/paper/2202.01913/) (2022)
- [Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/2106.02914/) (2021)
- [AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks](https://mlsanity.com/paper/2108.13591/) (2021)
- [Self Similarity Matrix based CNN Filter Pruning](https://mlsanity.com/paper/2211.01814/) (2022)
- [Compressive Feature Selection for Remote Visual Multi-Task Inference](https://mlsanity.com/paper/2405.09077/) (2024)

## Abstract (arXiv)

Building compact convolutional neural networks (CNNs) with reliable performance is a critical but challenging task, especially when deploying them in real-world applications. As a common approach to reduce the size of CNNs, pruning methods delete part of the CNN filters according to some metrics such as l1-norm. However, previous methods hardly leverage the information variance in a single feature map and the similarity characteristics among feature maps. In this paper, we propose a novel filter pruning method, which incorporates two kinds of feature map selections: diversity-aware selection (DFS) and similarity-aware selection (SFS). DFS aims to discover features with low information diversity while SFS removes features that have high similarities with others. We conduct extensive empirical experiments with various CNN architectures on publicly available datasets. The experimental results demonstrate that our model obtains up to 91.6% parameter decrease and 83.7% FLOPs reduction with almost no accuracy loss.