mlsanityData to 14 Oct 2026

Transferable Optimization Network for Cross-Domain Image Reconstruction

arXiv 2603.07831 ↗First posted 8 Mar 2026cs.CV cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

We develop a novel transfer learning framework to tackle the challenge of limited training data in image reconstruction problems. The proposed framework consists of two training steps, both of which are formed as bi-level optimizations. In the first step, we train a powerful universal feature-extractor that is capable of learning important knowledge from large, heterogeneous data sets in various domains. In the second step, we train a task-specific domain-adapter for a new target domain or task with only a limited amount of data available for training. Then the composition of the adapter and the universal feature-extractor effectively explores feature which serve as an important component of image regularization for the new domains, and this leads to high-quality reconstruction despite the data limitation issue. We apply this framework to reconstruct under-sampled MR images with limited data by using a collection of diverse data samples from different domains, such as images of other anatomies, measurements of various sampling ratios, and even different image modalities, including natural images. Experimental results demonstrate a promising transfer learning capability of the proposed method.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

27 of 45 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  5. 2014How transferable are features in deep neural networks?cited by 1,225
  6. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  7. 2017Learning multiple visual domains with residual adapterscited by 557
  8. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  9. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
  10. 2018A Survey on Deep Transfer Learningcited by 419
  11. 2020What is being transferred in transfer learning?cited by 368
  12. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
15 more
  1. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  2. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  3. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  4. 2022Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNetscited by 62
  5. 2025A Comprehensive Survey on Knowledge Distillationcited by 51
  6. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  7. 2022HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstructioncited by 30
  8. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  9. 2020Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstructioncited by 15
  10. 2021Universal Undersampled MRI Reconstructioncited by 15
  11. 2021Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstructioncited by 6
  12. 2025Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptationcited by 6
  13. 2023Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentationcited by 3
  14. 2023Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuningcited by 2
  15. 2025Knowledge Transfer from Interaction Learningcited by 2

Built on by

Not cited yet.