mlsanityData to 7 Oct 2026

EZCrop: Energy-Zoned Channels for Robust Output Pruning

arXiv 2105.03679 ↗First posted 8 May 2021eess.IV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent results have revealed an interesting observation in a trained convolutional neural network (CNN), namely, the rank of a feature map channel matrix remains surprisingly constant despite the input images. This has led to an effective rank-based channel pruning algorithm, yet the constant rank phenomenon remains mysterious and unexplained. This work aims at demystifying and interpreting such rank behavior from a frequency-domain perspective, which as a bonus suggests an extremely efficient Fast Fourier Transform (FFT)-based metric for measuring channel importance without explicitly computing its rank. We achieve remarkable CNN channel pruning based on this analytically sound and computationally efficient metric and adopt it for repetitive pruning to demonstrate robustness via our scheme named Energy-Zoned Channels for Robust Output Pruning (EZCrop), which shows consistently better results than other state-of-the-art channel pruning methods.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 8 May 2021.

Builds on

32 of 47 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  7. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  8. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  10. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 438
  11. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
  12. 2018Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptationcited by 295
20 more
  1. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  2. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  3. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  4. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  5. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 220
  6. 2017Data-Driven Sparse Structure Selection for Deep Neural Networkscited by 181
  7. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 145
  8. 2018The Singular Values of Convolutional Layerscited by 95
  9. 2020SCOP: Scientific Control for Reliable Neural Network Pruningcited by 92
  10. 2020Channel Pruning via Automatic Structure Searchcited by 84
  11. 2020EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruningcited by 80
  12. 2015Spectral Representations for Convolutional Neural Networkscited by 79
  13. 2019Pruning from Scratchcited by 72
  14. 2020Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compressioncited by 72
  15. 2020DMCP: Differentiable Markov Channel Pruning for Neural Networkscited by 68
  16. 2019Regularizing Activation Distribution for Training Binarized Deep Networkscited by 61
  17. 2020DHP: Differentiable Meta Pruning via HyperNetworkscited by 57
  18. 2018Automatically designing CNN architectures using genetic algorithm for image classificationcited by 48
  19. 2019CBNet: A Novel Composite Backbone Network Architecture for Object Detectioncited by 44
  20. 2015Compressing Convolutional Neural Networkscited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 1; 2026: 1.

6 papers.

  1. 2022What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Studycited by 3
  2. 2023Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Samplercited by 2
  3. 2023Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networkscited by 1
  4. 2024Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Taskscited by 1
  5. 2025LinDeps: A Fine-tuning Free Post-Pruning Method to Remove Layer-Wise Linear Dependencies with Guaranteed Performance Preservationcited by 1
  6. 2026Efficient Text-to-Audio Generation via Pruningcited by 0