mlsanityData to 14 Oct 2026

Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks

arXiv 2205.03602 ↗First posted 7 May 2022cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks are prevailing in deep learning tasks. However, they suffer from massive cost issues when working on mobile devices. Network pruning is an effective method of model compression to handle such problems. This paper presents a novel structured network pruning method with auxiliary gating structures which assigns importance marks to blocks in backbone network as a criterion when pruning. Block-wise pruning is then realized by proposed voting strategy, which is different from prevailing methods who prune a model in small granularity like channel-wise. We further develop a three-stage training scheduling for the proposed architecture incorporating knowledge distillation for better performance. Our experiments demonstrate that our method can achieve state-of-the-arts compression performance for the classification tasks. In addition, our approach can integrate synergistically with other pruning methods by providing pretrained models, thus achieving a better performance than the unpruned model with over 93% FLOPs reduced.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 7 May 2022.

Builds on

18 of 27 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  5. 2017Deep Mutual Learningcited by 628
  6. 2021Dynamic Neural Networks: A Surveycited by 408
  7. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  8. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  9. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 332
  10. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 315
  11. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  12. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
6 more
  1. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  2. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 149
  3. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 146
  4. 2021Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matchingcited by 79
  5. 2018The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videoscited by 69
  6. 2017Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Executioncited by 59

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GoPrune: Accelerated Structured Pruning with ℓ2,p-Norm Optimization
  2. 2025Structured Pruning and Quantization for Learned Image Compression
  3. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Survey
  4. 2024RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration
  5. 2019Structural Pruning in Deep Neural Networks: A Small-World Approach
  6. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
  7. 2021Deep Neural Compression Via Concurrent Pruning and Self-Distillation
  8. 2025Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression