# Learning Factorized Representations for Open-set Domain Adaptation

arXiv: https://arxiv.org/abs/1805.12277 · HTML: https://mlsanity.com/paper/1805.12277/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2018.

## Built on by (most cited first, 13 of 13)

- [Domain Adaptation under Open Set Label Shift](https://mlsanity.com/paper/2207.13048/) (2022)
- [Source-Free Progressive Graph Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2202.06174/) (2022)
- [Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection](https://mlsanity.com/paper/2206.02355/) (2022)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Conditional Extreme Value Theory for Open Set Video Domain Adaptation](https://mlsanity.com/paper/2109.00522/) (2021)
- [From Big to Small: Adaptive Learning to Partial-Set Domains](https://mlsanity.com/paper/2203.07375/) (2022)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model](https://mlsanity.com/paper/2407.14208/) (2024)
- [IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.12947/) (2022)
- [COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptation](https://mlsanity.com/paper/2401.17728/) (2024)
- [Trustworthy Representation Learning Across Domains](https://mlsanity.com/paper/2308.12315/) (2023)
- [Curricula for Learning Robust Policies with Factored State Representations in Changing Environments](https://mlsanity.com/paper/2409.09169/) (2024)
- [Opening the Scope of Openness in AI](https://mlsanity.com/paper/2505.06464/) (2025)

## Abstract (arXiv)

Domain adaptation for visual recognition has undergone great progress in the past few years. Nevertheless, most existing methods work in the so-called closed-set scenario, assuming that the classes depicted by the target images are exactly the same as those of the source domain. In this paper, we tackle the more challenging, yet more realistic case of open-set domain adaptation, where new, unknown classes can be present in the target data. While, in the unsupervised scenario, one cannot expect to be able to identify each specific new class, we aim to automatically detect which samples belong to these new classes and discard them from the recognition process. To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace. We therefore introduce a framework that factorizes the data into shared and private parts, while encouraging the shared representation to be discriminative. Our experiments on standard benchmarks evidence that our approach significantly outperforms the state-of-the-art in open-set domain adaptation.