Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

2023, Volume 24, Issue 11

Abstract

Keywords

Related Research

Back to Top

Frontiers of Information Technology & Electronic Engineering >> 2023, Volume 24, Issue 11 doi: 10.1631/FITEE.2200631

Dynamic parameterized learning for unsupervised domain adaptation

College of Intelligence and Computing, Tianjin University, Tianjin 300350, China; Tianjin Key Lab of Machine Learning, Tianjin University, Tianjin 300350, China;

Received: 2022-12-09 Accepted: 2023-12-04 Available online: 2023-12-04
HTML3 PDF 6 Collect 0

Next Previous

Abstract

enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between and learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the of and learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.

Related Research