# Adaptation Across Extreme Variations using Unlabeled Domain Bridges

arXiv: https://arxiv.org/abs/1906.02238 · HTML: https://mlsanity.com/paper/1906.02238/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

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

- [A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm](https://mlsanity.com/paper/2310.12244/) (2023)
- [Semantic Segmentation in Art Paintings](https://mlsanity.com/paper/2203.03238/) (2022)
- [Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation](https://mlsanity.com/paper/2302.02561/) (2023)
- [Graph-Relational Domain Adaptation](https://mlsanity.com/paper/2202.03628/) (2022)
- [Learning Semantic Segmentation from Multiple Datasets with Label Shifts](https://mlsanity.com/paper/2202.14030/) (2022)
- [Unsupervised Adaptation of Semantic Segmentation Models without Source Data](https://mlsanity.com/paper/2112.02359/) (2021)
- [Taxonomy-Structured Domain Adaptation](https://mlsanity.com/paper/2306.07874/) (2023)
- [Domain Adaptation for Real-World Single View 3D Reconstruction](https://mlsanity.com/paper/2108.10972/) (2021)
- [Towards Domain Adaptive Neural Contextual Bandits](https://mlsanity.com/paper/2406.09564/) (2024)

## Abstract (arXiv)

We tackle an unsupervised domain adaptation problem for which the domain discrepancy between labeled source and unlabeled target domains is large, due to many factors of inter and intra-domain variation. While deep domain adaptation methods have been realized by reducing the domain discrepancy, these are difficult to apply when domains are significantly unalike. In this work, we propose to decompose domain discrepancy into multiple but smaller, and thus easier to minimize, discrepancies by introducing unlabeled bridging domains that connect the source and target domains. We realize our proposal through an extension of the domain adversarial neural network with multiple discriminators, each of which accounts for reducing discrepancies between unlabeled (bridge, target) domains and a mix of all precedent domains including source. We validate the effectiveness of our method on several adaptation tasks including object recognition and semantic segmentation.