# Adaptation Across Extreme Variations using Unlabeled Domain Bridges

Source: [Adaptation Across Extreme Variations using Unlabeled Domain Bridges](<https://www.sota2.com/research/paper/68fa68371e209131cea1adc0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:32:00.581Z

Authors: Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker

Published: 2019-06-05T18:32:16.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1906.02238>)

[PDF](<https://arxiv.org/pdf/1906.02238.pdf>)