Can I read Unified Optimal Transport Framework for Universal Domain Adaptation on EtoBox?

Unified Optimal Transport Framework for Universal Domain Adaptation by Chang, Wanxing; Shi, Ye; Tuan, Hoang Duong; Wang, Jingya is a scholarly article available to read on EtoBox.

What is Unified Optimal Transport Framework for Universal Domain Adaptation about?

Universal Domain Adaptation (UniDA) aims to transfer knowledge from a source domain to a target domain without any constraints on label sets. Since both domains may hold private classes, identifying target common samples for domain alignment is an essential issue in UniDA. Most existing methods require manually specified or hand-tuned threshold values to detect common samples thus they are hard to extend to more realistic UniDA because of the diverse ratios of common classes. Moreover, they cannot recognize different categories among target-private samples as these private samples are treated as a whole. In this paper, we propose to use Optimal Transport (OT) to handle these issues under a unified framework, namely UniOT. First, an OT-based partial alignment with adaptive filling is designed to detect common classes without any predefined threshold values for realistic UniDA. It can automatically discover the intrinsic difference between common and private classes based on the statistical information of the assignment matrix obtained from OT. Second, we propose an OT-based target representation learning that encourages both global discrimination and local consistency of samples to

Author

Chang, Wanxing; Shi, Ye; Tuan, Hoang Duong; Wang, Jingya

Published

2022

Language

EN