# Self-ensembling for visual domain adaptation

arXiv: https://arxiv.org/abs/1706.05208 · HTML: https://mlsanity.com/paper/1706.05208/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2017.

## Built on by (most cited first, 12 of 12)

- [Transferability in Deep Learning: A Survey](https://mlsanity.com/paper/2201.05867/) (2022)
- [Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization](https://mlsanity.com/paper/2106.06916/) (2021)
- [Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training](https://mlsanity.com/paper/2405.02954/) (2024)
- [Transferrable Contrastive Learning for Visual Domain Adaptation](https://mlsanity.com/paper/2112.07516/) (2021)
- [Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection](https://mlsanity.com/paper/2303.11078/) (2023)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [Object Detectors in the Open Environment: Challenges, Solutions, and Outlook](https://mlsanity.com/paper/2403.16271/) (2024)
- [Say No to Freeloader: Protecting Intellectual Property of Your Deep Model](https://mlsanity.com/paper/2408.13161/) (2024)
- [S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation](https://mlsanity.com/paper/2408.15263/) (2024)
- [Randomized Dimension Reduction with Statistical Guarantees](https://mlsanity.com/paper/2310.01739/) (2023)
- [Long-Term Invariant Local Features via Implicit Cross-Domain Correspondences](https://mlsanity.com/paper/2311.03345/) (2023)
- [Self-trained Panoptic Segmentation](https://mlsanity.com/paper/2311.10648/) (2023)

## Abstract (arXiv)

This paper explores the use of self-ensembling for visual domain adaptation problems. Our technique is derived from the mean teacher variant (Tarvainen et al., 2017) of temporal ensembling (Laine et al;, 2017), a technique that achieved state of the art results in the area of semi-supervised learning. We introduce a number of modifications to their approach for challenging domain adaptation scenarios and evaluate its effectiveness. Our approach achieves state of the art results in a variety of benchmarks, including our winning entry in the VISDA-2017 visual domain adaptation challenge. In small image benchmarks, our algorithm not only outperforms prior art, but can also achieve accuracy that is close to that of a classifier trained in a supervised fashion.