paper-with-me

Papers

Input layer regularization and automated regularization hyperparameter tuning for myelin water estimation using deep learning

2025-01-30 · Mirage Modi, Shashank Sule, Jonathan Palumbo, Michael Rozowski, Mustapha Bouhrara, Wojciech Czaja, Richard G. Spencer

We propose a novel deep learning method which combines classical regularization with data augmentation for estimating myelin water fraction (MWF) in the brain via biexponential analysis. Our aim is to design an accurate deep learning technique for analysis of signals arising in magnetic resonance relaxometry. In particular, we study the biexponential model, one of the signal models used for MWF estimation. We greatly extend our previous work on \emph{input layer regularization (ILR)} in several ways. We now incorporate optimal regularization parameter selection via a dedicated neural network or generalized cross validation (GCV) on a signal-by-signal, or pixel-by-pixel, basis to form the augmented input signal, and now incorporate estimation of MWF, rather than just exponential time constants, into the analysis. On synthetically generated data, our proposed deep learning architecture outperformed both classical methods and a conventional multi-layer perceptron. On in vivo brain data, our architecture again outperformed other comparison methods, with GCV proving to be somewhat superior to a NN for regularization parameter selection. Thus, ILR improves estimation of MWF within the biexponential model. In addition, classical methods such as GCV may be combined with deep learning to optimize MWF imaging in the human brain.

📄 PDF Abstract BibTeX arXiv:2501.18074

Code (1)

ShashankSule/ILR-for-MWF 공식 구현 pytorch

Tasks

Data AugmentationDeep Learning

Similar Papers 제목 키워드 기반

Gradient-based bilevel optimization for multi-penalty Ridge regression through matrix differential calculus

2023-11-23 · Gabriele Maroni, Loris Cannelli, Dario Piga

Common regularization algorithms for linear regression, such as LASSO and Ridge regression, rely on a regularization hyperparameter that balances the tradeoff between minimizing the fitting error and the norm of the lear…

Bilevel OptimizationL2 Regularizationregression

Efficient multiple hyperparameter learning for log-linear models

2007-12-01 · NeurIPS 2007 12 · Chuan-Sheng Foo, Chuong B. Do, Andrew Y. Ng

Using multiple regularization hyperparameters is an effective method for managing model complexity in problems where input features have varying amounts of noise. While algorithms for choosing multiple hyperparameters ar…

PredictionStructured Prediction

Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction

2021-10-15 · CVPR 2022 1 · Sara Elkerdawy, Mostafa Elhoushi, Hong Zhang, Nilanjan Ray

Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely on learning a continuous channel gating …

Binary Classification

Conditional Deformable Image Registration with Spatially-Variant and Adaptive Regularization

2023-03-19 · Yinsong Wang, Huaqi Qiu, Chen Qin

Deep learning-based image registration approaches have shown competitive performance and run-time advantages compared to conventional image registration methods. However, existing learning-based approaches mostly require…

Hyperparameter OptimizationImage Registration

LiFT: Local Search via Linear Programming for Overfitting-Controlled Transformers

2026-06-15 · Abhishek Shukla, Anikeit Khanna, Ankur Sinha, Faiz Hamid arxiv

This paper proposes a Linear Programming (LP)-based local search framework for fine-tuning pretrained transformer models with explicit control against overfitting. The approach formulates transformer fine-tuning as a bil…

Bilevel Optimization