mlsanityData to 14 Oct 2026

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

arXiv 1811.00250 ↗First posted 1 Nov 2018cs.CVcited by 367

Not on the map. Why?

Abstract (arXiv)

Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM compresses CNN models by pruning filters with redundancy, rather than those with ''relatively less'' importance. When applied to two image classification benchmarks, our method validates its usefulness and strengths. Notably, on CIFAR-10, FPGM reduces more than 52% FLOPs on ResNet-110 with even 2.69% relative accuracy improvement. Moreover, on ILSVRC-2012, FPGM reduces more than 42% FLOPs on ResNet-101 without top-5 accuracy drop, which has advanced the state-of-the-art. Code is publicly available on GitHub: https://github.com/he-y/filter-pruning-geometric-median

Key facts. Cited by 367 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 98; 2022: 68; 2023: 76; 2024: 60; 2025: 48; 2026: 17.

367 papers.

Sort:

By area:

  1. 2023H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Modelscited by 832
  2. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  3. 2023Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Timecited by 252
  4. 2023DepGraph: Towards Any Structural Pruningcited by 203
  5. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 202
  6. 2023Structural Pruning for Diffusion Modelscited by 195
  7. 2021Patch Slimming for Efficient Vision Transformerscited by 133
  8. 2021Group Fisher Pruning for Practical Network Compressioncited by 131
  9. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  10. 2024Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methodscited by 82
  11. 2021MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edgecited by 79
  12. 2022Unified Visual Transformer Compressioncited by 79
38 more
  1. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
  2. 2021Convolutional Neural Network Pruning with Structural Redundancy Reductioncited by 73
  3. 2022SparCL: Sparse Continual Learning on the Edgecited by 55
  4. 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
  5. 2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
  6. 2023ZipLM: Inference-Aware Structured Pruning of Language Modelscited by 49
  7. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 49
  8. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 45
  9. 2022Learning to Weight Samples for Dynamic Early-exiting Networkscited by 44
  10. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  11. 2021IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantizationcited by 43
  12. 2021A Unified Pruning Framework for Vision Transformerscited by 40
  13. 2021When to Prune? A Policy towards Early Structural Pruningcited by 38
  14. 2023Dynamic Sparse Training with Structured Sparsitycited by 38
  15. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  16. 2021Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Modelcited by 37
  17. 2021Towards Compact CNNs via Collaborative Compressioncited by 36
  18. 2022SPDY: Accurate Pruning with Speedup Guaranteescited by 36
  19. 2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
  20. 2021CondenseNet V2: Sparse Feature Reactivation for Deep Networkscited by 34
  21. 2021Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Searchcited by 34
  22. 2021Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decompositioncited by 33
  23. 2023Dynamic Perceiver for Efficient Visual Recognitioncited by 33
  24. 2021Applications and Techniques for Fast Machine Learning in Sciencecited by 32
  25. 2022Learning Best Combination for Efficient N:M Sparsitycited by 32
  26. 2022Selective Network Linearization for Efficient Private Inferencecited by 31
  27. 2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
  28. 2021SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruningcited by 30
  29. 2021DECORE: Deep Compression with Reinforcement Learningcited by 29
  30. 2021Content-Aware GAN Compressioncited by 28
  31. 2024Exploring Token Pruning in Vision State Space Modelscited by 28
  32. 2021Locally Free Weight Sharing for Network Width Searchcited by 27
  33. 2023Latency-aware Unified Dynamic Networks for Efficient Image Recognitioncited by 26
  34. 2021Network Pruning That Matters: A Case Study on Retraining Variantscited by 25
  35. 2024SGLP: A Similarity Guided Fast Layer Partition Pruning for Compressing Large Deep Modelscited by 25
  36. 2021Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Predictioncited by 24
  37. 2021BCNet: Searching for Network Width with Bilaterally Coupled Networkcited by 23
  38. 2021On the Effect of Pruning on Adversarial Robustnesscited by 23

50 most cited of 367 All 367 (JSON)