mlsanityData to 7 Oct 2026

Scale-Space Hypernetworks for Efficient Biomedical Imaging

arXiv 2304.05448 ↗First posted 11 Apr 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (CNNs) are the predominant model used for a variety of medical image analysis tasks. At inference time, these models are computationally intensive, especially with volumetric data. In principle, it is possible to trade accuracy for computational efficiency by manipulating the rescaling factor in the downsample and upsample layers of CNN architectures. However, properly exploring the accuracy-efficiency trade-off is prohibitively expensive with existing models. To address this, we introduce Scale-Space HyperNetworks (SSHN), a method that learns a spectrum of CNNs with varying internal rescaling factors. A single SSHN characterizes an entire Pareto accuracy-efficiency curve of models that match, and occasionally surpass, the outcomes of training many separate networks with fixed rescaling factors. We demonstrate the proposed approach in several medical image analysis applications, comparing SSHN against strategies with both fixed and dynamic rescaling factors. We find that SSHN consistently provides a better accuracy-efficiency trade-off at a fraction of the training cost. Trained SSHNs enable the user to quickly choose a rescaling factor that appropriately balances accuracy and computational efficiency for their particular needs at inference.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 55 of its 80 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

55 of 80 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2016Pyramid Scene Parsing Networkcited by 2,472
38 more
  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  3. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  4. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  7. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  9. 2016HyperNetworkscited by 1,003
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  11. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  12. 2018VoxelMorph: A Learning Framework for Deformable Medical Image Registrationcited by 657
  13. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  14. 2020What is the State of Neural Network Pruning?cited by 578
  15. 2021Editing Factual Knowledge in Language Modelscited by 548
  16. 2019The State of Sparsity in Deep Neural Networkscited by 471
  17. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  18. 2018nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentationcited by 291
  19. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 283
  20. 2019Continual learning with hypernetworkscited by 267
  21. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 243
  22. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  23. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 211
  24. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  25. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  26. 2018Graph HyperNetworks for Neural Architecture Searchcited by 131
  27. 2016The Importance of Skip Connections in Biomedical Image Segmentationcited by 126
  28. 2019Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functionscited by 104
  29. 2018Stochastic Hyperparameter Optimization through Hypernetworkscited by 72
  30. 2019On Network Design Spaces for Visual Recognitioncited by 68
  31. 2019Hypernetwork functional image representationcited by 65
  32. 2017Bayesian Hypernetworkscited by 64
  33. 2019Squeeze-and-Attention Networks for Semantic Segmentationcited by 60
  34. 2014Fractional Max-Poolingcited by 35
  35. 2020A Learning Strategy for Contrast-agnostic MRI Segmentationcited by 35
  36. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
  37. 2017Implicit Weight Uncertainty in Neural Networkscited by 30
  38. 2019Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversioncited by 29

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.