mlsanityData to 14 Oct 2026

Self Similarity Matrix based CNN Filter Pruning

arXiv 2211.01814 ↗First posted 3 Nov 2022cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In recent years, most of the deep learning solutions are targeted to be deployed in mobile devices. This makes the need for development of lightweight models all the more imminent. Another solution is to optimize and prune regular deep learning models. In this paper, we tackle the problem of CNN model pruning with the help of Self-Similarity Matrix (SSM) computed from the 2D CNN filters. We propose two novel algorithms to rank and prune redundant filters which contribute similar activation maps to the output. One of the key features of our method is that there is no need of finetuning after training the model. Both the training and pruning process is completed simultaneously. We benchmark our method on two of the most popular CNN models - ResNet and VGG and record their performance on the CIFAR-10 dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 20 references that are in the map. First posted on arXiv 3 Nov 2022.

Builds on

18 of 20 references.

References · 18

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
  4. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  5. 2019On the Efficacy of Knowledge Distillationcited by 381
  6. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 378
  7. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  8. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  9. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 146
  10. 2019Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruningcited by 89
  11. 2015Neural Network Matrix Factorizationcited by 26
  12. 2020Parameter Space Factorization for Zero-Shot Learning across Tasks and Languagescited by 22
6 more
  1. 2019Filter Pruning by Switching to Neighboring CNNs with Good Attributescited by 15
  2. 2020Feature Statistics Guided Efficient Filter Pruningcited by 11
  3. 2022A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classificationcited by 11
  4. 2018SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Mannerscited by 7
  5. 2021Model Pruning Based on Quantified Similarity of Feature Mapscited by 6
  6. 2020A flexible, extensible software framework for model compression based on the LC algorithmcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression
  2. 2021Compact representations of convolutional neural networks via weight pruning and quantization
  3. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Framework
  4. 2024RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration
  5. 2025FAIR-Pruner: A Flexible Framework for Automatic Layer-Wise Pruning via Tolerance of Difference
  6. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Survey
  7. 2022Boosting Pruned Networks with Linear Over-parameterization
  8. 2019Structural Pruning in Deep Neural Networks: A Small-World Approach