mlsanityData to 7 Oct 2026

Network Pruning via Resource Reallocation

arXiv 2103.01847 ↗First posted 2 Mar 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network. Contemporary methods typically perform iterative pruning procedure from the original over-parameterized model, which is both tedious and expensive especially when the pruning is aggressive. In this paper, we propose a simple yet effective channel pruning technique, termed network Pruning via rEsource rEalLocation (PEEL), to quickly produce a desired slim model with negligible cost. Specifically, PEEL first constructs a predefined backbone and then conducts resource reallocation on it to shift parameters from less informative layers to more important layers in one round, thus amplifying the positive effect of these informative layers. To demonstrate the effectiveness of PEEL , we perform extensive experiments on ImageNet with ResNet-18, ResNet-50, MobileNetV2, MobileNetV3-small and EfficientNet-B0. Experimental results show that structures uncovered by PEEL exhibit competitive performance with state-of-the-art pruning algorithms under various pruning settings. Our code is available at https://github.com/cardwing/Codes-for-PEEL.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 2 Mar 2021.

Builds on

30 of 37 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2019Searching for MobileNetV3cited by 1,984
  9. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  10. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,059
  11. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  12. 2018Rethinking the Value of Network Pruningcited by 595
18 more
  1. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 491
  2. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  3. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  4. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  5. 2019Structured Knowledge Distillation for Dense Predictioncited by 277
  6. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  7. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  8. 2018Discrimination-aware Channel Pruning for Deep Neural Networkscited by 171
  9. 2019Learning Lightweight Lane Detection CNNs by Self Attention Distillationcited by 162
  10. 2020SCOP: Scientific Control for Reliable Neural Network Pruningcited by 92
  11. 2018AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inferencecited by 77
  12. 2019Towards Efficient Model Compression via Learned Global Rankingcited by 75
  13. 2020Good Subnetworks Provably Exist: Pruning via Greedy Forward Selectioncited by 70
  14. 2020DMCP: Differentiable Markov Channel Pruning for Neural Networkscited by 68
  15. 2020Inter-Region Affinity Distillation for Road Marking Segmentationcited by 58
  16. 2018Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networkscited by 19
  17. 2019Deeply-supervised Knowledge Synergycited by 18
  18. 2018Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilizationcited by 10

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 1.

6 papers.

  1. 2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
  2. 2021RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Mergingcited by 19
  3. 2023DynamicKD: An Effective Knowledge Distillation via Dynamic Entropy Correction-Based Distillation for Gap Optimizingcited by 7
  4. 2021Self-supervised Feature-Gate Coupling for Dynamic Network Pruningcited by 0
  5. 2023Semantic-embedded Similarity Prototype for Scene Recognitioncited by 0
  6. 2024PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimatorcited by 0