mlsanityData to 13 Oct 2026

An Entropy-based Pruning Method for CNN Compression

arXiv 1706.05791 ↗First posted 19 Jun 2017cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

This paper aims to simultaneously accelerate and compress off-the-shelf CNN models via filter pruning strategy. The importance of each filter is evaluated by the proposed entropy-based method first. Then several unimportant filters are discarded to get a smaller CNN model. Finally, fine-tuning is adopted to recover its generalization ability which is damaged during filter pruning. Our method can reduce the size of intermediate activations, which would dominate most memory footprint during model training stage but is less concerned in previous compression methods. Experiments on the ILSVRC-12 benchmark demonstrate the effectiveness of our method. Compared with previous filter importance evaluation criteria, our entropy-based method obtains better performance. We achieve 3.3x speed-up and 16.64x compression on VGG-16, 1.54x acceleration and 1.47x compression on ResNet-50, both with about 1% top-5 accuracy decrease.

Key facts. Cited by 37 papers in the map (data through 13 Oct 2026). First posted on arXiv 19 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 7; 2024: 10; 2025: 5; 2026: 3.

37 papers.

Sort:

By area:

  1. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  2. 2024SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Modelscited by 24
  3. 2023Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?cited by 20
  4. 2021Reversible Watermarking in Deep Convolutional Neural Networks for Integrity Authenticationcited by 17
  5. 2021Blending Pruning Criteria for Convolutional Neural Networkscited by 13
  6. 2025FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Modelscited by 9
  7. 2022Complexity-Driven CNN Compression for Resource-constrained Edge AIcited by 8
  8. 2024An Effective Information Theoretic Framework for Channel Pruningcited by 7
  9. 2022Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networkscited by 6
  10. 2022Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruningcited by 5
  11. 2023Efficient CNNs via Passive Filter Pruningcited by 5
  12. 2022Pruning for Feature-Preserving Circuits in CNNscited by 4
25 more
  1. 2024Layer Collapse Can be Induced by Unstructured Pruningcited by 4
  2. 2024What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Biascited by 4
  3. 2023Pruning Before Training May Improve Generalization, Provablycited by 3
  4. 2025Stratified Knowledge-Density Super-Network for Scalable Vision Transformerscited by 3
  5. 2022CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusioncited by 2
  6. 2023Differentiable Weight Masks for Domain Transfercited by 2
  7. 2021Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristiccited by 1
  8. 2021Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Datacited by 1
  9. 2022Efficient Similarity-based Passive Filter Pruning for Compressing CNNscited by 1
  10. 2023Edge AI for Internet of Energy: Challenges and Perspectivescited by 1
  11. 2024Decay Pruning Method: Smooth Pruning With a Self-Rectifying Procedurecited by 1
  12. 2024A Survey of Fragile Model Watermarkingcited by 1
  13. 2026Routing the Lottery: Adaptive Subnetworks for Heterogeneous Datacited by 1
  14. 2022Neural Network Compression via Effective Filter Analysis and Hierarchical Pruningcited by 0
  15. 2022Embedding Compression for Text Classification Using Dictionary Screeningcited by 0
  16. 2023The Road to On-board Change Detection: A Lightweight Patch-Level Change Detection Network via Exploring the Potential of Pruning and Poolingcited by 0
  17. 2024Efficient Parameter Mining and Freezing for Continual Object Detectioncited by 0
  18. 2024Towards Generalized Entropic Sparsification for Convolutional Neural Networkscited by 0
  19. 2024Efficient DNN-Powered Software with Fair Sparse Modelscited by 0
  20. 2024Lightweight Design and Optimization methods for DCNNs: Progress and Futurescited by 0
  21. 2025ICE-Pruning: An Iterative Cost-Efficient Pruning Pipeline for Deep Neural Networkscited by 0
  22. 2025Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networkscited by 0
  23. 2025Teacher-Guided One-Shot Pruning via Context-Aware Knowledge Distillationcited by 0
  24. 2026Denoised Variance-Based Pruning with Optimal Brain Bias Compensationcited by 0
  25. 2026FedASAP: Activation Statistics-driven Structured Adaptive Pruning for Efficient Personalized Federated Learning for Lesion Segmentation on brain MRIcited by 0