Separation of Unknown Features and Samples for Unbiased Source-free Open Set Domain Adaptation
Authors:
- Fu LiFLFu Li
- Yifan LanYLYifan Lan
- Yuwu LuYLYuwu Lu
- Wai Keung WongWWWai Keung Wong
- Ming ZhaoMZMing Zhao
- Zhihui LaiZLZhihui Lai
- Xuelong LiXLXuelong Li
- 13 April 2025
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 166
Abstract
No abstract availableFunding Information
- Basic and Applied Basic Research Foundation of Guangdong Province (2022A1515140099, 2023A1515012875)
- National Natural Science Foundation of China (62076129, 62176162)
This publication has 26 references indexed in Scilit:
- Knowledge Transfer with Simulated Inter-image Erasing for Weakly Supervised Semantic Segmentation2024
- Source-Free Domain Adaptation via Distribution Estimation2022
- Domain Consensus Clustering for Universal Domain Adaptation2021
- Learning to Detect Open Classes for Universal Domain Adaptation2020
- Learning to Balance Specificity and Invariance for In and Out of Domain Generalization2020
- Visual Commonsense R-CNN2020
- Separate to Adapt: Open Set Domain Adaptation via Progressive Separation2019
- Open Set Domain Adaptation by Backpropagation2018
- Deep Hashing Network for Unsupervised Domain Adaptation2017
- Independent component analysis, A new concept?Signal Processing, 1994