# IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2210.12947 · HTML: https://mlsanity.com/paper/2210.12947/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 62 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 26 of 26)

- [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)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)
- [Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation](https://mlsanity.com/paper/2010.05862/) (2020)
- [On the Effectiveness of Image Rotation for Open Set Domain Adaptation](https://mlsanity.com/paper/2007.12360/) (2020)
- [Towards Inheritable Models for Open-Set Domain Adaptation](https://mlsanity.com/paper/2004.04388/) (2020)
- [Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.12087/) (2020)
- [A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation](https://mlsanity.com/paper/2003.02541/) (2020)
- [Open Set Domain Adaptation: Theoretical Bound and Algorithm](https://mlsanity.com/paper/1907.08375/) (2019)
- [Deep Residual Correction Network for Partial Domain Adaptation](https://mlsanity.com/paper/2004.04914/) (2020)
- [KL Guided Domain Adaptation](https://mlsanity.com/paper/2106.07780/) (2021)
- [Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation](https://mlsanity.com/paper/2006.06567/) (2020)
- [Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis](https://mlsanity.com/paper/2104.05703/) (2021)
- [Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation](https://mlsanity.com/paper/2012.03358/) (2020)
- [Learning Factorized Representations for Open-set Domain Adaptation](https://mlsanity.com/paper/1805.12277/) (2018)
- [Attract or Distract: Exploit the Margin of Open Set](https://mlsanity.com/paper/1908.01925/) (2019)
- [Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptation](https://mlsanity.com/paper/2110.12635/) (2021)
- [Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation](https://mlsanity.com/paper/2006.13022/) (2020)
- [Improving Unsupervised Domain Adaptation with Variational Information Bottleneck](https://mlsanity.com/paper/1911.09310/) (2019)

## Built on by (most cited first, 3 of 3)

- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2405.17774/) (2024)
- [CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference](https://mlsanity.com/paper/2605.31591/) (2026)

## Abstract (arXiv)

Distribution shift between train (source) and test (target) datasets is a common problem encountered in machine learning applications. One approach to resolve this issue is to use the Unsupervised Domain Adaptation (UDA) technique that carries out knowledge transfer from a label-rich source domain to an unlabeled target domain. Outliers that exist in either source or target datasets can introduce additional challenges when using UDA in practice. In this paper, α-divergence is used as a measure to minimize the discrepancy between the source and target distributions while inheriting robustness, adjustable with a single parameter α, as the prominent feature of this measure. Here, it is shown that the other well-known divergence-based UDA techniques can be derived as special cases of the proposed method. Furthermore, a theoretical upper bound is derived for the loss in the target domain in terms of the source loss and the initial α-divergence between the two domains. The robustness of the proposed method is validated through testing on several benchmarked datasets in open-set and partial UDA setups where extra classes existing in target and source datasets are considered as outliers.