mlsanityData to 7 Oct 2026

AACP: Model Compression by Accurate and Automatic Channel Pruning

arXiv 2102.00390 ↗First posted 31 Jan 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Channel pruning is formulated as a neural architecture search (NAS) problem recently. However, existing NAS-based methods are challenged by huge computational cost and inflexibility of applications. How to deal with multiple sparsity constraints simultaneously and speed up NAS-based channel pruning are still open challenges. In this paper, we propose a novel Accurate and Automatic Channel Pruning (AACP) method to address these problems. Firstly, AACP represents the structure of a model as a structure vector and introduces a pruning step vector to control the compressing granularity of each layer. Secondly, AACP utilizes Pruned Structure Accuracy Estimator (PSAE) to speed up the performance estimation process. Thirdly, AACP proposes Improved Differential Evolution (IDE) algorithm to search the optimal structure vector effectively. Because of IDE, AACP can deal with FLOPs constraint and model size constraint simultaneously and efficiently. Our method can be easily applied to various tasks and achieve state of the art performance. On CIFAR10, our method reduces 65% FLOPs of ResNet110 with an improvement of 0.26% top-1 accuracy. On ImageNet, we reduce 42% FLOPs of ResNet50 with a small loss of 0.18% top-1 accuracy and reduce 30% FLOPs of MobileNetV2 with a small loss of 0.7% top-1 accuracy. The source code will be released after publication.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 31 Jan 2021.

Builds on

31 of 43 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  9. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  10. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  11. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  12. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
19 more
  1. 2018Rethinking the Value of Network Pruningcited by 595
  2. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  3. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  4. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  5. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  6. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  7. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  8. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  9. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  10. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  11. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  12. 2017Data-Driven Sparse Structure Selection for Deep Neural Networkscited by 181
  13. 2018Discrimination-aware Channel Pruning for Deep Neural Networkscited by 171
  14. 2020Channel Pruning via Automatic Structure Searchcited by 84
  15. 2018AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inferencecited by 77
  16. 2019Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structurecited by 76
  17. 2019Pruning from Scratchcited by 72
  18. 2016Learning the Number of Neurons in Deep Networkscited by 69
  19. 2020DMCP: Differentiable Markov Channel Pruning for Neural Networkscited by 68

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 1.

4 papers.

  1. 2021ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Searchcited by 4
  2. 2021AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritancecited by 1
  3. 2022Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Surveycited by 1
  4. 2023Filter Pruning via Filters Similarity in Consecutive Layerscited by 1