# Learning Cross-domain Generalizable Features by Representation Disentanglement

arXiv: https://arxiv.org/abs/2003.00321 · HTML: https://mlsanity.com/paper/2003.00321/

## Key facts

- Cited by 6 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 29 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation](https://mlsanity.com/paper/2103.12857/) (2021)
- [Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrieval](https://mlsanity.com/paper/2103.12328/) (2021)
- [Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience](https://mlsanity.com/paper/2308.03175/) (2023)
- [Application of Computer Vision and Machine Learning for Digitized Herbarium Specimens: A Systematic Literature Review](https://mlsanity.com/paper/2104.08732/) (2021)
- [Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation](https://mlsanity.com/paper/2503.23623/) (2025)

## Abstract (arXiv)

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features in a target domain is an interesting and difficult problem that is rarely discussed in the current literature. This problem is essential for many real-world applications such as improving diagnostic classification or prediction in medical imaging. To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract generalizable features that enable transferring knowledge to unseen categorical features in target domains. The proposed MIDNet is developed as a semi-supervised learning paradigm to alleviate the dependency on labeled data. This is important for practical applications where data annotation requires rare expertise as well as intense time and labor. We demonstrate our method on handwritten digits datasets and a fetal ultrasound dataset for image classification tasks. Experiments show that our method outperforms the state-of-the-art and achieve expected performance with sparsely labeled data.