TY - GEN
T1 - Recent research advances in Novel Class Discovery
AU - Su, Yuetong
AU - Wei, Baoguo
AU - Wang, Xinyu
AU - Li, Xu
AU - Li, Lixin
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - catastrophic forgetting
KW - Novel Class Discovery
KW - self-supervised techniques
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85217750831&partnerID=8YFLogxK
U2 - 10.1109/ISCTech63666.2024.10845265
DO - 10.1109/ISCTech63666.2024.10845265
M3 - 会议稿件
AN - SCOPUS:85217750831
T3 - 2024 12th International Conference on Information Systems and Computing Technology, ISCTech 2024
BT - 2024 12th International Conference on Information Systems and Computing Technology, ISCTech 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Conference on Information Systems and Computing Technology, ISCTech 2024
Y2 - 8 November 2024 through 11 November 2024
ER -