mlsanityData to 7 Oct 2026

Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression

arXiv 2003.08935 ↗First posted 19 Mar 2020cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

In this paper, we analyze two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense. By simply changing the way the sparsity regularization is enforced, filter pruning and low-rank decomposition can be derived accordingly. This provides another flexible choice for network compression because the techniques complement each other. For example, in popular network architectures with shortcut connections (e.g. ResNet), filter pruning cannot deal with the last convolutional layer in a ResBlock while the low-rank decomposition methods can. In addition, we propose to compress the whole network jointly instead of in a layer-wise manner. Our approach proves its potential as it compares favorably to the state-of-the-art on several benchmarks.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 10; 2023: 23; 2024: 12; 2025: 4; 2026: 1.

72 papers.

Sort:

By area:

  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  3. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  4. 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 76
  5. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
  6. 2022Revisiting Random Channel Pruning for Neural Network Compressioncited by 50
  7. 2024Q-VLM: Post-training Quantization for Large Vision-Language Modelscited by 47
  8. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  9. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  10. 2021Towards Compact CNNs via Collaborative Compressioncited by 36
  11. 2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
  12. 2023OTOV2: Automatic, Generic, User-Friendlycited by 32
38 more
  1. 2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
  2. 2021GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarizationcited by 29
  3. 2024Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratchcited by 20
  4. 2021Towards Efficient Graph Convolutional Networks for Point Cloud Handlingcited by 18
  5. 2021Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Setcited by 18
  6. 2024Lightweight Pixel Difference Networks for Efficient Visual Representation Learningcited by 17
  7. 2023TinyTracker: Ultra-Fast and Ultra-Low-Power Edge Vision In-Sensor for Gaze Estimationcited by 16
  8. 2023Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLOcited by 15
  9. 2021Generalizable Mixed-Precision Quantization via Attribution Rank Preservationcited by 11
  10. 2023Automatic Attention Pruning: Improving and Automating Model Pruning using Attentionscited by 11
  11. 2024ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networkscited by 11
  12. 2022Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithmcited by 9
  13. 2022ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learningcited by 9
  14. 2021Deep Model Compression based on the Training Historycited by 7
  15. 2021Toward Compact Deep Neural Networks via Energy-Aware Pruningcited by 6
  16. 2021EZCrop: Energy-Zoned Channels for Robust Output Pruningcited by 6
  17. 2023OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operatorscited by 6
  18. 2021Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusioncited by 5
  19. 2022Pruning-aware Sparse Regularization for Network Pruningcited by 5
  20. 2023Dynamic Structure Pruning for Compressing CNNscited by 5
  21. 2024MINI-LLM: Memory-Efficient Structured Pruning for Large Language Modelscited by 5
  22. 2021Deeplite Neutrino: An End-to-End Framework for Constrained Deep Learning Model Optimizationcited by 4
  23. 2021Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracycited by 4
  24. 2023Progressive Channel-Shrinking Networkcited by 4
  25. 2024REPrune: Channel Pruning via Kernel Representative Selectioncited by 4
  26. 2024HESSO: Towards Automatic Efficient and User Friendly Any Neural Network Training and Pruningcited by 4
  27. 2022Adaptive Activation-based Structured Pruningcited by 3
  28. 2022Compact Model Training by Low-Rank Projection with Energy Transfercited by 3
  29. 2024Deep learning-based blind image super-resolution with iterative kernel reconstruction and noise estimationcited by 3
  30. 2024Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Compositioncited by 3
  31. 2025One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compressioncited by 3
  32. 2021Batch Normalization Tells You Which Filter is Importantcited by 2
  33. 2023Filter Pruning based on Information Capacity and Independencecited by 2
  34. 2023Iterative Soft Shrinkage Learning for Efficient Image Super-Resolutioncited by 2
  35. 2023Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Samplercited by 2
  36. 2023LAPP: Layer Adaptive Progressive Pruning for Compressing CNNs from Scratchcited by 2
  37. 2023AdaFlood: Adaptive Flood Regularizationcited by 2
  38. 2024Shapley Pruning for Neural Network Compressioncited by 2

50 most cited of 72 All 72 (JSON)