FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation

11/18/2020
by   Jaemin Na, et al.
0

Unsupervised domain adaptation (UDA) methods for learning domain invariant representations have achieved remarkable progress. However, few studies have been conducted on the case of large domain discrepancies between a source and a target domain. 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.

READ FULL TEXT

page 3

page 6

research
02/21/2022

Domain-Augmented Domain Adaptation

Unsupervised domain adaptation (UDA) enables knowledge transfer from the...
research
12/06/2018

Disjoint Label Space Transfer Learning with Common Factorised Space

In this paper, a unified approach is presented to transfer learning that...
research
10/08/2020

Distributionally Robust Learning for Unsupervised Domain Adaptation

We propose a distributionally robust learning (DRL) method for unsupervi...
research
10/08/2019

ATL: Autonomous Knowledge Transfer from Many Streaming Processes

Transferring knowledge across many streaming processes remains an unchar...
research
09/12/2023

Strong-Weak Integrated Semi-supervision for Unsupervised Single and Multi Target Domain Adaptation

Unsupervised domain adaptation (UDA) focuses on transferring knowledge l...
research
03/25/2018

Unsupervised Domain Adaptation: A Multi-task Learning-based Method

This paper presents a novel multi-task learning-based method for unsuper...
research
06/14/2022

Confidence Score for Source-Free Unsupervised Domain Adaptation

Source-free unsupervised domain adaptation (SFUDA) aims to obtain high p...

Please sign up or login with your details

Forgot password? Click here to reset