Data to 14 Oct 2026

Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks

arXiv 1808.06866 ↗First posted 21 Aug 2018cs.CVcited by 315

Not on the map. Why?

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

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 72; 2022: 74; 2023: 65; 2024: 52; 2025: 38; 2026: 14.

315 papers.

Sort:

By area:

2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
2023DepGraph: Towards Any Structural Pruningcited by 203
2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
2024Compact Language Models via Pruning and Knowledge Distillationcited by 148
2021Group Fisher Pruning for Practical Network Compressioncited by 131
2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
2022Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformercited by 108
2021Dynamic Slimmable Networkcited by 83
2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 79
2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
2021Convolutional Neural Network Pruning with Structural Redundancy Reductioncited by 73

38 more

2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
2022SparCL: Sparse Continual Learning on the Edgecited by 55
2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
2022ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsitycited by 45
2021Manifold Regularized Dynamic Network Pruningcited by 43
2022Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equationscited by 43
2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
2022Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attentioncited by 35
2021Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decompositioncited by 33
2022Learning Best Combination for Efficient N:M Sparsitycited by 32
2023OTOV2: Automatic, Generic, User-Friendlycited by 32
2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
2021Efficient Neural Network Training via Forward and Backward Propagation Sparsificationcited by 30
2024MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metriccited by 30
2021Content-Aware GAN Compressioncited by 28
2024Exploring Token Pruning in Vision State Space Modelscited by 28
2021Locally Free Weight Sharing for Network Width Searchcited by 27
2021TransTailor: Pruning the Pre-trained Model for Improved Transfer Learningcited by 25
2021Network Pruning That Matters: A Case Study on Retraining Variantscited by 25
2024SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Modelscited by 25
2021Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Predictioncited by 24
2021BCNet: Searching for Network Width with Bilaterally Coupled Networkcited by 23
2021Carrying out CNN Channel Pruning in a White Boxcited by 22
2021ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximationscited by 21
2024Isomorphic Pruning for Vision Modelscited by 21
2022CNN Filter DB: An Empirical Investigation of Trained Convolutional Filterscited by 20
2022Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptionscited by 20
2023SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channelscited by 20
2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratchcited by 20
2021RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networkscited by 19
2021RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Mergingcited by 19
2021A Unified Approach to Coreset Learningcited by 18
2024OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimizationcited by 18

50 most cited of 315 All 315 (JSON)