Adaptation Across Extreme Variations using Unlabeled Domain Bridges

By Shuyang Dai, Kihyuk Sohn, Yi-Hsuan Tsai, Lawrence Carin, Manmohan Chandraker. 2019

13 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cancer Research, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Fei Pan
2. Seokju Lee
3. Inkyu Shin
4. In-So Kweon
5. François Rameau

In Representation & Self-Supervised Learning

1. In-So Kweon
2. Yingli Tian
3. Longlong Jing

Citations in the corpus

• Unsupervised Intra-Domain Adaptation for Semantic Segmentation Through Self-Supervision (2020, background): “To generalize this concept, [7] decomposes the domain discrepancy into multiple smaller discrepancies by introducing unlabeled intermediate domains.”