FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

By Jaemin Na, Heechul Jung, HyungJin Chang, Wonjun Hwang. 2020

266 citations recorded by the source corpus.

Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, most of the studies were based on direct adaptation from the source domain to the target domain and have suffered from large domain discrepancies. In this paper, we propose a UDA method that effectively handles such large domain discrepancies. We introduce a fixed ratio-based mixup to augment multiple intermediate domains between the source and target domain. From the augmented-domains, we train the source-dominant model and the target-dominant model that have complementary characteristics. Using our confidence-based learning methodologies, e.g., bidirectional matching with high-confidence predictions and self-penalization using low-confidence predictions, the models can learn from each other or from its own results. Through our proposed methods, the models gradually transfer domain knowledge from the source to the target domain. Extensive experiments demonstrate the superiority of our proposed method on three public benchmarks: Office-31, Office-Home, and VisDA-2017. 1

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, background): “Step 4 [30,31,32,33,34,35,36,37,38,39] Sneakers, Notebook, Backpack, Alarm Clock, Push Pin, Paper Clip, Batteries, Radio, Fan, Ruler”
A Survey on Negative Transfer (2020, methodology): “[80] introduced a selective learning algorithm (SLA) to identify target-related data from the source and intermediate domains based on the assumption that similar data can be reconstructed via the same auto-encoder.”
Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks (2021, background): “Different works in this area (Bousmalis et al., 2016; 2017; Na et al., 2020; Wang & Breckon, 2020; Kang et al., 2019) try to learn diverse domain independent representations using the source domain to make predictions, such as image classiﬁcation, in the target domains.”