# Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1808.06866 · HTML: https://mlsanity.com/paper/1808.06866/

## Key facts

- Cited by 315 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2018.

## Built on by (most cited first, 30 of 315)

- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations](https://mlsanity.com/paper/2308.06767/) (2023)
- [Compact Language Models via Pruning and Knowledge Distillation](https://mlsanity.com/paper/2407.14679/) (2024)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer](https://mlsanity.com/paper/2210.06707/) (2022)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge](https://mlsanity.com/paper/2110.14032/) (2021)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Convolutional Neural Network Pruning with Structural Redundancy Reduction](https://mlsanity.com/paper/2104.03438/) (2021)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [SparCL: Sparse Continual Learning on the Edge](https://mlsanity.com/paper/2209.09476/) (2022)
- [Residual Local Feature Network for Efficient Super-Resolution](https://mlsanity.com/paper/2205.07514/) (2022)
- [Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework](https://mlsanity.com/paper/2107.12422/) (2021)
- [Revisiting Random Channel Pruning for Neural Network Compression](https://mlsanity.com/paper/2205.05676/) (2022)
- [ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity](https://mlsanity.com/paper/2208.02507/) (2022)
- [Manifold Regularized Dynamic Network Pruning](https://mlsanity.com/paper/2103.05861/) (2021)
- [Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations](https://mlsanity.com/paper/2205.13571/) (2022)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [CHEX: CHannel EXploration for CNN Model Compression](https://mlsanity.com/paper/2203.15794/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention](https://mlsanity.com/paper/2209.13802/) (2022)
- [Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition](https://mlsanity.com/paper/2107.11442/) (2021)
- [Learning Best Combination for Efficient N:M Sparsity](https://mlsanity.com/paper/2206.06662/) (2022)
- [OTOV2: Automatic, Generic, User-Friendly](https://mlsanity.com/paper/2303.06862/) (2023)
- [Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning](https://mlsanity.com/paper/2102.03214/) (2021)
- [Efficient Neural Network Training via Forward and Backward Propagation Sparsification](https://mlsanity.com/paper/2111.05685/) (2021)

## Abstract (arXiv)

This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pre-trained model. Large capacity enables SFP to train from scratch and prune the model simultaneously. In contrast, previous filter pruning methods should be conducted on the basis of the pre-trained model to guarantee their performance. Empirically, SFP from scratch outperforms the previous filter pruning methods. Moreover, our approach has been demonstrated effective for many advanced CNN architectures. Notably, on ILSCRC-2012, SFP reduces more than 42% FLOPs on ResNet-101 with even 0.2% top-5 accuracy improvement, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/soft-filter-pruning