Deep Long-tailed Data Learning towards Visual Recognition
Speaker: 
Yiu-Ming CHEUNG
Chair Professor in Artificial Intelligence,
Department of Computer Science
Hong Kong Baptist University
| Date: Time: Venue: | | 23 October 2026, Friday 10:30am – 11:30am School of Computing & Information Systems 1 (SCIS 1)
Level 5, Meeting Room 5-1
Singapore Management University
Singapore 178902
Please register by 22 October 2026 
|
|
About the Talk
Although deep learning has made great progress, a good model often requires a large amount of artificially balanced and annotated data. Unfortunately, real-world data are often unbalanced, typically exhibiting a long-tailed distribution, which refers to a small number of classes with abundant training samples but the remaining large number of classes only with very few training instances. Under the circumstances, the performance of deep learning models trained on long-tailed data declines sharply in the tail classes. However, tail classes cannot be ignored in various situations such as rare disease diagnosis, and anomaly detection. Subsequently, long-tailed data is still very challenging to deep learning. In this talk, the impact of long-tailed data on deep learning models will be first introduced. Then, the research progress in this area will be reviewed, including some representative methods in the literature. Lastly, the potential research directions in this field will be discussed.
About the Speaker
Yiu-ming CHEUNG is currently the Chair Professor (Artificial Intelligence) in the Department of Computer Science, Associate Dean for the Faculty of Science and Technology, Dean of the Institute for Research and Continuing Education (IRACE), and Associate Director of the Institute of Computational and Theoretical Studies at Hong Kong Baptist University (HKBU). He received his PhD from the Department of Computer Science and Engineering at the Chinese University of Hong Kong. In recognition of his dedication and exceptional achievements, he has been elected a Member of the European Academy of Sciences and Arts (EASA), a Fellow of the Institute of Electrical and Electronics Engineers (IEEE), the American Association for the Advancement of Science (AAAS), the International Association for Pattern Recognition (IAPR), the Institution of Engineering and Technology (IET), and British Computer Society (BCS). Besides, he has been elected a Distinguished Lecturer of the IEEE Computational Intelligence Society and named Chair Professor in the Changjiang Scholars Program by the Ministry of Education of the People’s Republic of China. Professor Cheung’s research interests include machine learning and visual computing, with applications in data science, pattern recognition, multi-objective optimization, and information security. He has published over 300 articles in leading conferences and journals, e.g., TPAMI, TNNLS, TIFS, TIP, TMM, TKDE, TCYB, CVPR, NeurIPS, ICML, IJCAI, and AAAI. He is the recipient of: (1) 2023-2024 RGC Senior Research Fellow Award, (2) the President’s Award for Outstanding Performance in Scholarly Work (2023–2024), and (3) the 2023 APNNS Outstanding Achievement Award, among others.
This seminar is co-organized by IEEE CIS Chapter.
