# Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaboration

arXiv: https://arxiv.org/abs/1904.13179 · HTML: https://mlsanity.com/paper/1904.13179/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [Domain Adaptation under Open Set Label Shift](https://mlsanity.com/paper/2207.13048/) (2022)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Generalized Domain Adaptation](https://mlsanity.com/paper/2106.01656/) (2021)
- [Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence](https://mlsanity.com/paper/2407.18899/) (2024)
- [Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge](https://mlsanity.com/paper/2102.06271/) (2021)
- [Weakly-Supervised Domain Adaptation with Proportion-Constrained Pseudo-Labeling](https://mlsanity.com/paper/2506.22301/) (2025)
- [Evaluation of Deep Neural Network Domain Adaptation Techniques for Image Recognition](https://mlsanity.com/paper/2109.13420/) (2021)
- [Domain Adaptation for Learning Generator from Paired Few-Shot Data](https://mlsanity.com/paper/2102.12765/) (2021)

## Abstract (arXiv)

In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and not all classes are shared between these two domains. Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting. We consider this problem as weakly supervised open-set domain adaptation. To address this practical setting, we propose the Collaborative Distribution Alignment (CDA) method, which performs knowledge transfer bilaterally and works collaboratively to classify unlabeled data and identify outlier samples. Extensive experiments on the Office benchmark and an application on person reidentification show that our method achieves state-of-the-art performance.