# Online Filter Clustering and Pruning for Efficient Convnets

arXiv: https://arxiv.org/abs/1905.11787 · HTML: https://mlsanity.com/paper/1905.11787/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2019.

## Built on by (most cited first, 6 of 6)

- [Convolutional Neural Network Pruning with Structural Redundancy Reduction](https://mlsanity.com/paper/2104.03438/) (2021)
- [Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training](https://mlsanity.com/paper/2307.00368/) (2023)
- [Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning](https://mlsanity.com/paper/2311.02003/) (2023)
- [Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss](https://mlsanity.com/paper/2205.01997/) (2022)
- [Computer Vision Model Compression Techniques for Embedded Systems: A Survey](https://mlsanity.com/paper/2408.08250/) (2024)
- [Neural expressiveness for beyond importance model compression](https://mlsanity.com/paper/2512.06440/) (2025)

## Abstract (arXiv)

Pruning filters is an effective method for accelerating deep neural networks (DNNs), but most existing approaches prune filters on a pre-trained network directly which limits in acceleration. Although each filter has its own effect in DNNs, but if two filters are the same with each other, we could prune one safely. In this paper, we add an extra cluster loss term in the loss function which can force filters in each cluster to be similar online. After training, we keep one filter in each cluster and prune others and fine-tune the pruned network to compensate for the loss. Particularly, the clusters in every layer can be defined firstly which is effective for pruning DNNs within residual blocks. Extensive experiments on CIFAR10 and CIFAR100 benchmarks demonstrate the competitive performance of our proposed filter pruning method.