mlsanityData to 7 Oct 2026

Pruning Filters for Efficient ConvNets

arXiv 1608.08710 ↗First posted 31 Aug 2016cs.CV cs.LGcited by 1,129

Not on the map. Why?

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

Abstract (arXiv)

The success of CNNs in various applications is accompanied by a significant increase in the computation and parameter storage costs. Recent efforts toward reducing these overheads involve pruning and compressing the weights of various layers without hurting original accuracy. However, magnitude-based pruning of weights reduces a significant number of parameters from the fully connected layers and may not adequately reduce the computation costs in the convolutional layers due to irregular sparsity in the pruned networks. We present an acceleration method for CNNs, where we prune filters from CNNs that are identified as having a small effect on the output accuracy. By removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly. In contrast to pruning weights, this approach does not result in sparse connectivity patterns. Hence, it does not need the support of sparse convolution libraries and can work with existing efficient BLAS libraries for dense matrix multiplications. We show that even simple filter pruning techniques can reduce inference costs for VGG-16 by up to 34% and ResNet-110 by up to 38% on CIFAR10 while regaining close to the original accuracy by retraining the networks.

Key facts. Cited by 1,129 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 2; 2020: 0; 2021: 257; 2022: 232; 2023: 215; 2024: 179; 2025: 148; 2026: 95.

1,129 papers.

Sort:

By area:

  1. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  2. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  3. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  4. 2023Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningcited by 408
  5. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  6. 2023A Survey on Model Compression for Large Language Modelscited by 263
  7. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  8. 2021I-BERT: Integer-only BERT Quantizationcited by 250
  9. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 228
  10. 2023Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessmentcited by 227
  11. 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modificationscited by 220
  12. 2024The Unreasonable Ineffectiveness of the Deeper Layerscited by 219
38 more
  1. 2023DepGraph: Towards Any Structural Pruningcited by 202
  2. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  3. 2023Structural Pruning for Diffusion Modelscited by 193
  4. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  5. 2021Learning N:M Fine-grained Structured Sparse Neural Networks From Scratchcited by 177
  6. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  7. 2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
  8. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  9. 2021Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuningcited by 145
  10. 2021Patch Slimming for Efficient Vision Transformerscited by 131
  11. 2021Group Fisher Pruning for Practical Network Compressioncited by 130
  12. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  13. 2023The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reductioncited by 120
  14. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  15. 2021Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Maskscited by 103
  16. 2022Monarch: Expressive Structured Matrices for Efficient and Accurate Trainingcited by 100
  17. 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Modelscited by 98
  18. 2021Scalable Vision Transformers with Hierarchical Poolingcited by 84
  19. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  20. 2021Dynamic Slimmable Networkcited by 83
  21. 2021Sparse Training via Boosting Pruning Plasticity with Neuroregenerationcited by 83
  22. 2021Leveraging Sparse Linear Layers for Debuggable Deep Networkscited by 82
  23. 2024Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methodscited by 80
  24. 2022Unified Visual Transformer Compressioncited by 79
  25. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 76
  26. 2021Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Modelscited by 75
  27. 2021Convolutional Neural Network Pruning with Structural Redundancy Reductioncited by 73
  28. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
  29. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
  30. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 66
  31. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insightscited by 65
  32. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
  33. 2022Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scalecited by 64
  34. 2021Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracycited by 62
  35. 2021A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustnesscited by 62
  36. 2021Pufferfish: Communication-efficient Models At No Extra Costcited by 61
  37. 2023Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMscited by 61
  38. 2021Handcrafted Backdoors in Deep Neural Networkscited by 57

50 most cited of 1,129 All 1,129 (JSON)