Scale-Space Hypernetworks for Efficient Biomedical Imaging

• URL: http://arxiv.org/abs/2304.05448v2
• Date: Thu, 29 Jun 2023 16:34:47 GMT
• Title: Scale-Space Hypernetworks for Efficient Biomedical Imaging
• Authors: Jose Javier Gonzalez Ortiz, John Guttag, Adrian Dalca
• Abstract summary: We introduce Scale-Space HyperNetworks (SSHN), a method that learns a spectrum of CNNs with varying internal rescaling factors. SSHN consistently provides a better accuracy-efficiency trade-off at a fraction of the training cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• CSWin-UNet: Transformer UNet with Cross-Shaped Windows for Medical Image Segmentation [22.645013853519]
  CSWin-UNet is a novel U-shaped segmentation method that incorporates the CSWin self-attention mechanism into the UNet. Our empirical evaluations on diverse datasets, including synapse multi-organ CT, cardiac MRI, and skin lesions, demonstrate that CSWin-UNet maintains low model complexity while delivering high segmentation accuracy.
  arXiv  Detail & Related papers  (2024-07-25T14:25:17Z)
• Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations [49.173541207550485]
  Adaptive Meshing By Expert Reconstruction (AMBER) is an imitation learning problem. AMBER combines a graph neural network with an online data acquisition scheme to predict the projected sizing field of an expert mesh. We experimentally validate AMBER on 2D meshes and 3D meshes provided by a human expert, closely matching the provided demonstrations and outperforming a single-step CNN baseline.
  arXiv  Detail & Related papers  (2024-06-20T10:01:22Z)
• Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization [7.392278887917975]
  We propose a mixed-precision post training quantization approach that assigns different numerical precisions to tensors in a network based on their specific needs. Our experiments demonstrate latency reductions compared to a 16-bit baseline of $25.48%$, $21.69%$, and $33.28%$ respectively.
  arXiv  Detail & Related papers  (2023-06-08T02:18:58Z)
• SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters [19.062678788410434]
  We consider the Hessian matrix during network training. We show that Sharpness Adjusted Number of Effective parameters (SANE) is robust to large learning rates. We provide evidence and the Hessian shifts across "loss basins" at large learning rates.
  arXiv  Detail & Related papers  (2023-05-29T13:29:31Z)
• Adversarial training with informed data selection [53.19381941131439]
  Adrial training is the most efficient solution to defend the network against these malicious attacks. This work proposes a data selection strategy to be applied in the mini-batch training. The simulation results show that a good compromise can be obtained regarding robustness and standard accuracy.
  arXiv  Detail & Related papers  (2023-01-07T12:09:50Z)
• Precision Machine Learning [5.15188009671301]
  We compare various function approximation methods and study how they scale with increasing parameters and data. We find that neural networks can often outperform classical approximation methods on high-dimensional examples. We develop training tricks which enable us to train neural networks to extremely low loss, close to the limits allowed by numerical precision.
  arXiv  Detail & Related papers  (2022-10-24T17:58:30Z)
• CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics [13.38218193857018]
  Convolutional neural networks (CNNs) have demonstrated extraordinarily good performance in many computer vision tasks. CNNPruner allows users to interactively create pruning plans according to a desired goal on model size or accuracy.
  arXiv  Detail & Related papers  (2020-09-08T02:08:20Z)
• Learning to Learn Parameterized Classification Networks for Scalable Input Images [76.44375136492827]
  Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. We employ meta learners to generate convolutional weights of main networks for various input scales. We further utilize knowledge distillation on the fly over model predictions based on different input resolutions.
  arXiv  Detail & Related papers  (2020-07-13T04:27:25Z)
• Calibrating Deep Neural Networks using Focal Loss [77.92765139898906]
  Miscalibration is a mismatch between a model's confidence and its correctness. We show that focal loss allows us to learn models that are already very well calibrated. We show that our approach achieves state-of-the-art calibration without compromising on accuracy in almost all cases.
  arXiv  Detail & Related papers  (2020-02-21T17:35:50Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.