mlsanityData to 14 Oct 2026

Efficient CNNs via Passive Filter Pruning

arXiv 2304.02319 ↗First posted 5 Apr 2023cs.LG cs.AI cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks (CNNs) have shown state-of-the-art performance in various applications. However, CNNs are resource-hungry due to their requirement of high computational complexity and memory storage. Recent efforts toward achieving computational efficiency in CNNs involve filter pruning methods that eliminate some of the filters in CNNs based on the enquoteimportance of the filters. The majority of existing filter pruning methods are either "active", which use a dataset and generate feature maps to quantify filter importance, or "passive", which compute filter importance using entry-wise norm of the filters without involving data. Under a high pruning ratio where large number of filters are to be pruned from the network, the entry-wise norm methods eliminate relatively smaller norm filters without considering the significance of the filters in producing the node output, resulting in degradation in the performance. To address this, we present a passive filter pruning method where the filters are pruned based on their contribution in producing output by considering the operator norm of the filters. The proposed pruning method generalizes better across various CNNs compared to that of the entry-wise norm-based pruning methods. In comparison to the existing active filter pruning methods, the proposed pruning method is at least 4.5 times faster in computing filter importance and is able to achieve similar performance compared to that of the active filter pruning methods. The efficacy of the proposed pruning method is evaluated on audio scene classification and image classification using various CNNs architecture such as VGGish, DCASE21Net, VGG-16 and ResNet-50.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 35 of its 56 references that are in the map. First posted on arXiv 5 Apr 2023.

Builds on

35 of 56 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  7. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  8. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  9. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  10. 2016CNN Architectures for Large-Scale Audio Classificationcited by 704
  11. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  12. 2021AST: Audio Spectrogram Transformercited by 643
23 more
  1. 2018Rethinking the Value of Network Pruningcited by 599
  2. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 574
  3. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  4. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
  5. 2015Recent Advances in Convolutional Neural Networkscited by 360
  6. 2014Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluationcited by 306
  7. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 295
  8. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  9. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  10. 2013Predicting Parameters in Deep Learningcited by 224
  11. 2021Block Pruning For Faster Transformerscited by 177
  12. 2022Structured Pruning Learns Compact and Accurate Modelscited by 170
  13. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 146
  14. 2018Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layerscited by 112
  15. 2018AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inferencecited by 77
  16. 2018A multi-device dataset for urban acoustic scene classificationcited by 75
  17. 2014On the Computational Efficiency of Training Neural Networkscited by 71
  18. 2022Masked Spectrogram Prediction For Self-Supervised Audio Pre-Trainingcited by 51
  19. 2017An Entropy-based Pruning Method for CNN Compressioncited by 37
  20. 2019Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehiclescited by 25
  21. 2021Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systemscited by 14
  22. 2022A Passive Similarity based CNN Filter Pruning for Efficient Acoustic Scene Classificationcited by 11
  23. 2021Toward Compact Deep Neural Networks via Energy-Aware Pruningcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 2; 2026: 2.

5 papers.

  1. 2023E-PANNs: Sound Recognition Using Efficient Pre-trained Audio Neural Networkscited by 4
  2. 2025Integrating Pruning with Quantization for Efficient Deep Neural Networks Compressioncited by 0
  3. 2025Compressing Quaternion Convolutional Neural Networks for Audio Classificationcited by 0
  4. 2026Efficient Text-to-Audio Generation via Pruningcited by 0
  5. 2026Investigating catastrophic forgetting in sound event classificationcited by 0