# Tackling Partial Domain Adaptation with Self-Supervision

arXiv: https://arxiv.org/abs/1906.05199 · HTML: https://mlsanity.com/paper/1906.05199/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Generalized Domain Adaptation](https://mlsanity.com/paper/2106.01656/) (2021)
- [Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation](https://mlsanity.com/paper/2107.02067/) (2021)
- [Unsupervised Domain Adaptation for Video Transformers in Action Recognition](https://mlsanity.com/paper/2207.12842/) (2022)
- [A separability-based approach to quantifying generalization: which layer is best?](https://mlsanity.com/paper/2405.01524/) (2024)
- [Self-Supervision & Meta-Learning for One-Shot Unsupervised Cross-Domain Detection](https://mlsanity.com/paper/2106.03496/) (2021)
- [Learning from Synthetic InSAR with Vision Transformers: The case of volcanic unrest detection](https://mlsanity.com/paper/2201.03016/) (2022)
- [Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation](https://mlsanity.com/paper/2410.11271/) (2024)
- [Exploring Data Aggregation and Transformations to Generalize across Visual Domains](https://mlsanity.com/paper/2108.09208/) (2021)

## Abstract (arXiv)

Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains. They allow to train reliable models that work over datasets of different nature (photos, paintings etc), but they still struggle when the domains do not share an identical label space. In the partial domain adaptation setting, where the target covers only a subset of the source classes, it is challenging to reduce the domain gap without incurring in negative transfer. Many solutions just keep the standard domain adaptation techniques by adding heuristic sample weighting strategies. In this work we show how the self-supervisory signal obtained from the spatial co-location of patches can be used to define a side task that supports adaptation regardless of the exact label sharing condition across domains. We build over a recent work that introduced a jigsaw puzzle task for domain generalization: we describe how to reformulate this approach for partial domain adaptation and we show how it boosts existing adaptive solutions when combined with them. The obtained experimental results on three datasets supports the effectiveness of our approach.