mlsanityData to 7 Oct 2026

ClassPruning: Speed Up Image Restoration Networks by Dynamic N:M Pruning

arXiv 2211.05488 ↗First posted 10 Nov 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration difficulty, and then the sparse subnetworks with different capabilities can be sampled based on predicted difficulty by performing dynamic N:M fine-grained structured pruning on base restoration networks. We further propose a novel training strategy along with two additional loss terms to stabilize training and improve performance. Experiments demonstrate that ClassPruning can help existing methods save approximately 40% FLOPs while maintaining performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 68 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

56 of 68 references.

References · 56

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  9. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  10. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  11. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
38 more
  1. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  2. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  3. 2021Multi-Stage Progressive Image Restorationcited by 813
  4. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 722
  5. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  6. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  7. 2013Network In Networkcited by 600
  8. 2016Learning Structured Sparsity in Deep Neural Networkscited by 538
  9. 2016Adaptive Computation Time for Recurrent Neural Networkscited by 479
  10. 2017Benchmarking Single Image Dehazing and Beyondcited by 445
  11. 2016Deep Joint Rain Detection and Removal from a Single Imagecited by 351
  12. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  13. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  14. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 324
  15. 2020Learning Enriched Features for Real Image Restoration and Enhancementcited by 311
  16. 2019FFA-Net: Feature Fusion Attention Network for Single Image Dehazingcited by 307
  17. 2013Learning Factored Representations in a Deep Mixture of Expertscited by 275
  18. 2019What's Hidden in a Randomly Weighted Neural Network?cited by 236
  19. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  20. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  21. 2021Accelerating Sparse Deep Neural Networkscited by 213
  22. 2020CycleISP: Real Image Restoration via Improved Data Synthesiscited by 212
  23. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  24. 2018Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Derainingcited by 205
  25. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 205
  26. 2017Image De-raining Using a Conditional Generative Adversarial Networkcited by 197
  27. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
  28. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  29. 2018Residual Dense Network for Image Restorationcited by 181
  30. 2021Learning N:M Fine-grained Structured Sparse Neural Networks From Scratchcited by 177
  31. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  32. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
  33. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  34. 2018Gated Context Aggregation Network for Image Dehazing and Derainingcited by 89
  35. 2021Dynamic Slimmable Networkcited by 83
  36. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
  37. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77
  38. 2017Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Executioncited by 59

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.