# Semi-supervised Deep Transfer for Regression without Domain Alignment

arXiv: https://arxiv.org/abs/2509.05092 · HTML: https://mlsanity.com/paper/2509.05092/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 5 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization](https://mlsanity.com/paper/2001.03360/) (2020)
- [Rank consistent ordinal regression for neural networks with application to age estimation](https://mlsanity.com/paper/1901.07884/) (2019)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2003.00343/) (2020)
- [BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation](https://mlsanity.com/paper/2204.02811/) (2022)
- [ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation](https://mlsanity.com/paper/2205.14566/) (2022)
- [Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method](https://mlsanity.com/paper/1910.12384/) (2019)
- [EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction](https://mlsanity.com/paper/2111.05100/) (2021)
- [Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation](https://mlsanity.com/paper/2107.06735/) (2021)
- [About Pyramid Structure in Convolutional Neural Networks](https://mlsanity.com/paper/1608.04064/) (2016)
- [Target-agnostic Source-free Domain Adaptation for Regression Tasks](https://mlsanity.com/paper/2312.00540/) (2023)
- [Learning from Different Samples: A Source-free Framework for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2411.06665/) (2024)

## Abstract (arXiv)

Deep learning models deployed in real-world applications (e.g., medicine) face challenges because source models do not generalize well to domain-shifted target data. Many successful domain adaptation (DA) approaches require full access to source data. Yet, such requirements are unrealistic in scenarios where source data cannot be shared either because of privacy concerns or because it is too large and incurs prohibitive storage or computational costs. Moreover, resource constraints may limit the availability of labeled targets. We illustrate this challenge in a neuroscience setting where source data are unavailable, labeled target data are meager, and predictions involve continuous-valued outputs. We build upon Contradistinguisher (CUDA), an efficient framework that learns a shared model across the labeled source and unlabeled target samples, without intermediate representation alignment. Yet, CUDA was designed for unsupervised DA, with full access to source data, and for classification tasks. We develop CRAFT -- a Contradistinguisher-based Regularization Approach for Flexible Training -- for source-free (SF), semi-supervised transfer of pretrained models in regression tasks. We showcase the efficacy of CRAFT in two neuroscience settings: gaze prediction with electroencephalography (EEG) data and ``brain age'' prediction with structural MRI data. For both datasets, CRAFT yielded up to 9% improvement in root-mean-squared error (RMSE) over fine-tuned models when labeled training examples were scarce. Moreover, CRAFT leveraged unlabeled target data and outperformed four competing state-of-the-art source-free domain adaptation models by more than 3%. Lastly, we demonstrate the efficacy of CRAFT on two other real-world regression benchmarks. We propose CRAFT as an efficient approach for source-free, semi-supervised deep transfer for regression that is ubiquitous in biology and medicine.