mlsanityData to 7 Oct 2026

Pruning Very Deep Neural Network Channels for Efficient Inference

arXiv 2211.08339 ↗First posted 14 Nov 2022cs.CVcited by 0

Not on the map. Why?

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 enhances 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. Our code has been made publicly available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 53 of its 78 references that are in the map. First posted on arXiv 14 Nov 2022.

Builds on

53 of 78 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2015Fast R-CNNcited by 2,930
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
38 more
  1. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  3. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  4. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  5. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  6. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  7. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  8. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  9. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  10. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 304
  11. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 298
  12. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
  13. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  14. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  15. 2015Net2Net: Accelerating Learning via Knowledge Transfercited by 245
  16. 2014cuDNN: Efficient Primitives for Deep Learningcited by 240
  17. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  18. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  19. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
  20. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  21. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 189
  22. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
  23. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  24. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  25. 2019Feature Selective Anchor-Free Module for Single-Shot Object Detectioncited by 139
  26. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  27. 2015Data-free parameter pruning for Deep Neural Networkscited by 112
  28. 2015Accelerating Very Deep Convolutional Networks for Classification and Detectioncited by 109
  29. 2015Fast Algorithms for Convolutional Neural Networkscited by 102
  30. 2013Fast Training of Convolutional Networks through FFTscited by 89
  31. 2015Fast ConvNets Using Group-wise Brain Damagecited by 81
  32. 2016Learning the Number of Neurons in Deep Networkscited by 69
  33. 2014Fast Convolutional Nets With fbfft: A GPU Performance Evaluationcited by 27
  34. 2015Diversity Networks: Neural Network Compression Using Determinantal Point Processescited by 25
  35. 2019MoBiNet: A Mobile Binary Network for Image Classificationcited by 15
  36. 2016LCNN: Lookup-based Convolutional Neural Networkcited by 11
  37. 2019Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networkscited by 5
  38. 2016Compact Deep Convolutional Neural Networks With Coarse Pruningcited by 3

50 most cited of 53 All 53 (JSON)

Built on by

Not cited yet.