# Transferable Optimization Network for Cross-Domain Image Reconstruction

arXiv: https://arxiv.org/abs/2603.07831 · HTML: https://mlsanity.com/paper/2603.07831/

## 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 (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [What is being transferred in transfer learning?](https://mlsanity.com/paper/2008.11687/) (2020)
- [A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1704.02422/) (2017)
- [Surgical Fine-Tuning Improves Adaptation to Distribution Shifts](https://mlsanity.com/paper/2210.11466/) (2022)
- [Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning](https://mlsanity.com/paper/2102.03983/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets](https://mlsanity.com/paper/2208.07463/) (2022)
- [A Comprehensive Survey on Knowledge Distillation](https://mlsanity.com/paper/2503.12067/) (2025)
- [A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networks](https://mlsanity.com/paper/1710.02615/) (2017)
- [HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction](https://mlsanity.com/paper/2203.08213/) (2022)
- [An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset](https://mlsanity.com/paper/2110.00715/) (2021)
- [Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction](https://mlsanity.com/paper/2007.11245/) (2020)
- [Universal Undersampled MRI Reconstruction](https://mlsanity.com/paper/2103.05214/) (2021)
- [Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction](https://mlsanity.com/paper/2104.12939/) (2021)
- [Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation](https://mlsanity.com/paper/2501.15377/) (2025)
- [Med-Tuning: A New Parameter-Efficient Tuning Framework for Medical Volumetric Segmentation](https://mlsanity.com/paper/2304.10880/) (2023)
- [Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuning](https://mlsanity.com/paper/2311.02003/) (2023)
- [Knowledge Transfer from Interaction Learning](https://mlsanity.com/paper/2509.18733/) (2025)

## 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.