Recent research advances in Novel Class Discovery

Yuetong Su, Baoguo Wei, Xinyu Wang, Xu Li, Lixin Li

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Novel Class Discovery (NCD) has emerged as a vital area of research in machine learning and computer vision, aiming to identify novel classes in unlabeled datasets by leveraging knowledge from labeled datasets. Recent advances in NCD, especially after 2023, have focused on addressing key challenges such as imbalanced data, catastrophic forgetting, and improving the generalization capabilities of models. We examine how recent works integrate incremental learning, self-supervised techniques, and uncertainty quantification to enhance the discovery of novel classes. The role of generative models and transfer learning is also highlighted, particularly in domain-specific applications such as remote sensing, biomedical data, and synthetic aperture radar (SAR) imagery. Our review provides insights into the strengths, limitations, and future directions of NCD research, focusing on scalability, interpretability, and real-world applicability.

源语言英语
主期刊名2024 12th International Conference on Information Systems and Computing Technology, ISCTech 2024
出版商Institute of Electrical and Electronics Engineers Inc.
ISBN(电子版)9798350379860
DOI
出版状态已出版 - 2024
活动12th International Conference on Information Systems and Computing Technology, ISCTech 2024 - Xi'an, 中国
期限: 8 11月 202411 11月 2024

出版系列

姓名2024 12th International Conference on Information Systems and Computing Technology, ISCTech 2024

会议

会议12th International Conference on Information Systems and Computing Technology, ISCTech 2024
国家/地区中国
Xi'an
时期8/11/2411/11/24

指纹

探究 'Recent research advances in Novel Class Discovery' 的科研主题。它们共同构成独一无二的指纹。

引用此