期刊论文

Zhou, ZH

英文

Expert Systems with Applications

0957-4174

2025

261

125460

10.1016/j.eswa.2024.125460

National Key Research and Development Program of China [2022YFF0607001]; Guangdong Basic and Applied Basic Research Foundation, China [2023A1515010993]; Guangdong Provincial Key Laboratory of Human Digital Twin [2022B12 12010004]; Guangzhou City Science and Technology Research Projects, China [2023B01J0011]; Jiangmen Science and Technology Research Projects, China [2021080200070009151]; Shaoguan Science and Technology Research Project, China [230316116276286]; Foshan Science and Technology Research Project, China [2220001018608]; Zhuhai Science and Technology Research Project, China [2320004002668]

本校为其他机构

Unsupervised Domain Adaptation (UDA) leverages a labeled source domain to solve tasks in an unlabeled target domain. While Transformer-based methods have shown promise in UDA, their application is limited to plain Transformers, excluding Convolutional Neural Networks (CNNs) and hierarchical Transformers. To address this issues, we propose Bidirectional Probability Calibration (BiPC) from a probability space perspective. We demonstrate that the probability outputs from a pre-trained head, after extensive pre-training, are robust against domain gaps and can adjust the probability distribution of...