文献类型：期刊文献

英文题名：GCL-OSDA: Uncertainty prediction-based graph collaborative learning for open-set domain adaptation

作者：Dai, Yiwen[1];Zhu, Hongqing[1];Yang, Suyi[2];Zhang, Han[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Kings Coll London, Dept Math Nat & Engn Sci, London WC2R 2LS, England

年份：2022

卷号：256

外文期刊名：KNOWLEDGE-BASED SYSTEMS

收录：;EI(收录号：20223812761489);WOS:【SCI-EXPANDED(收录号:WOS:000860566400009)】；

基金：Acknowledgements The authors would like to thank anonymous reviewers for their helpful comments and suggestions. This work was sup- ported by the National Nature Science Foundation of China under Grant 61872143.

语种：英文

外文关键词：Open -set domain adaptation; Evidence theory; Graph convolution network; Graph collaborative learning; Uncertainty prediction

摘要：Open-set domain adaptation (OSDA), which allows the target domain to store invisible class samples in the source domain, has recently received significant attention. In this paper, we propose a new unsupervised OSDA classification framework using an evidential network and multi-binary classifier and consider their jointly selected samples as a pseudo-labelled sample set of an unknown class. Specifically, this study designed an evidential network based on the D-S evidence theory to predict the degree of belief that a sample belongs to an unknown class. By selecting samples with high -uncertainty, false positive samples can be removed, which improves the reliability of unknown sample selection. Then, to better explore the intra-class relationship, an open-set graph convolutional network (OSGC) is proposed to extract distinguishable features of known and unknown samples in a weighted adversarial adaptation manner. Moreover, this paper presents a graph collaborative learning strategy to retrain the unknown recognition module (URM) with high confidence pseudo-labelled samples, which is predicted by the graph convolution network (GCN), where the target known class distribution is learned. Experimental results show that the proposed method outperforms state-of-the-art OSDA algorithms on three benchmark datasets and maintains a high recognition accuracy for unknown classes over a wide range of openness. (C) 2022 Elsevier B.V. All rights reserved.