mlsanityData to 14 Oct 2026

Channel Pruning for Accelerating Very Deep Neural Networks

arXiv 1707.06168 ↗First posted 19 Jul 2017cs.CVcited by 702

Not on the map. Why?

Cited by 20 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks.Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhance the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5x speed-up along with only 0.3% increase of error. More importantly, our method is able to accelerate modern networks like ResNet, Xception and suffers only 1.4%, 1.0% accuracy loss under 2x speed-up respectively, which is significant. Code has been made publicly available.

Key facts. Cited by 702 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 198; 2022: 154; 2023: 143; 2024: 97; 2025: 70; 2026: 39.

702 papers.

Sort:

By area:

  1. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  2. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  3. 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 385
  4. 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruningcited by 322
  5. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  6. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  7. 2024The Unreasonable Ineffectiveness of the Deeper Layerscited by 226
  8. 2021Accelerating Sparse Deep Neural Networkscited by 223
  9. 2023DepGraph: Towards Any Structural Pruningcited by 203
  10. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
  11. 2023Structural Pruning for Diffusion Modelscited by 195
  12. 2021Chasing Sparsity in Vision Transformers: An End-to-End Explorationcited by 183
38 more
  1. 2021Adaptive Token Sampling For Efficient Vision Transformerscited by 183
  2. 2022Structured Pruning Learns Compact and Accurate Modelscited by 170
  3. 2022A Fast Post-Training Pruning Framework for Transformerscited by 162
  4. 2022On-Device Training Under 256KB Memorycited by 160
  5. 2024Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Modelscited by 146
  6. 2021Patch Slimming for Efficient Vision Transformerscited by 133
  7. 2021Group Fisher Pruning for Practical Network Compressioncited by 131
  8. 2021IA-RED2: Interpretability-Aware Redundancy Reduction for Vision Transformerscited by 127
  9. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  10. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 115
  11. 2021Federated Unlearning via Class-Discriminative Pruningcited by 115
  12. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  13. 2021The Efficiency Misnomercited by 98
  14. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 89
  15. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 86
  16. 2022The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Trainingcited by 85
  17. 2021Dynamic Slimmable Networkcited by 83
  18. 2024GPTVQ: The Blessing of Dimensionality for LLM Quantizationcited by 82
  19. 2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 79
  20. 2022Unified Visual Transformer Compressioncited by 79
  21. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
  22. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  23. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
  24. 2022Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Spacecited by 66
  25. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 65
  26. 2023QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Modelscited by 64
  27. 2021A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustnesscited by 62
  28. 2024Dynamic Diffusion Transformercited by 62
  29. 2024MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Routercited by 62
  30. 2021Pufferfish: Communication-efficient Models At No Extra Costcited by 61
  31. 2023SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformercited by 60
  32. 2024Finding Transformer Circuits with Edge Pruningcited by 60
  33. 2023MixFormerV2: Efficient Fully Transformer Trackingcited by 57
  34. 2022Advancing Model Pruning via Bi-level Optimizationcited by 56
  35. 2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
  36. 2023UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformerscited by 54
  37. 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
  38. 2021A Survey on Green Deep Learningcited by 52

50 most cited of 702 All 702 (JSON)