Deep Learning of the Unknowns: Anomaly and Out-of-distribution Detection Perspectives
[CFAR Rising Star Lecture Series]
Deep Learning of the Unknowns: Anomaly and Out-of-distribution Detection Perspectives (Hybrid event) by Dr. Pang Guansong
Being able to say no to abnormal/unknown instances is one key capability that machine learning systems should master in broad real-world application domains, especially for security/safety-critical domains, e.g., detecting and rejecting suspicious financial crimes in banking, handling unknown objects in autonomous driving or medical artificial intelligence (AI) systems, etc. Anomaly and out-of-distribution detection are two lines of research that could achieve this capability. While current approaches have resulted in substantially improved detection accuracy in both research lines, uncovering the unknowns still remains an open problem due to the difficulty in obtaining instances of the unknowns and their unbounded distribution.
In this talk, Dr. Pang Guansong from the Singapore Management University (SMU) will review relevant progress and introduce some of his team’s recent work on tackling the challenges in anomaly and out-of-distribution detection.
Deep Learning of the Unknowns: Anomaly and Out-of-distribution Detection Perspectives (Hybrid event) by Dr. Pang Guansong
30 Nov 2022 | 10.00am (Singapore Time)
Being able to say no to abnormal/unknown instances is one key capability that machine learning systems should master in broad real-world application domains, especially for security/safety-critical domains, e.g., detecting and rejecting suspicious financial crimes in banking, handling unknown objects in autonomous driving or medical artificial intelligence (AI) systems, etc. Anomaly and out-of-distribution detection are two lines of research that could achieve this capability. While current approaches have resulted in substantially improved detection accuracy in both research lines, uncovering the unknowns still remains an open problem due to the difficulty in obtaining instances of the unknowns and their unbounded distribution.
In this talk, Dr. Pang Guansong from the Singapore Management University (SMU) will review relevant progress and introduce some of his team’s recent work on tackling the challenges in anomaly and out-of-distribution detection.
SPEAKER
Dr. Pang Guansong
Assistant Professor
School of Computing and Information Systems
Singapore Management University (SMU)
Assistant Professor
School of Computing and Information Systems
Singapore Management University (SMU)
Dr. Pang Guansong is a tenure-track Assistant Professor of Computer Science at the School of Computing and Information Systems, Singapore Management University (SMU). He was previously a Research Fellow at the Australian Institute for Machine Learning, University of Adelaide, Australia. Dr. Pang obtained his PhD degree at University of Technology Sydney in 2019. His research interest generally lies in data mining, machine learning, and their applications, with a research theme focused on abnormal, rare, or unknown instance detection and robust, generalised learning algorithms for creating trustworthy continual AI systems.
Dr. Pang has published more than 40 papers in refereed conferences and journals, such as KDD, CVPR, ICCV, ECCV, AAAI, IJCAI, ACM MM, WSDM, IEEE TKDE, IEEE TMM, IEEE TMI, ACM CSUR, ACM TKDD, JAIR, and DMKDJ. He also serves the community as a (senior) program committee member or reviewer of these venues. As an organiser of the anomaly and novelty detection workshop series, IJCAI-AI4AN 2020-2021 and KDD-ANDEA 2021-2022, Dr. Pang is also an Editorial Board member of IEEE Intelligent Systems and International Journal of Data Science and Analytics.
Dr. Pang has published more than 40 papers in refereed conferences and journals, such as KDD, CVPR, ICCV, ECCV, AAAI, IJCAI, ACM MM, WSDM, IEEE TKDE, IEEE TMM, IEEE TMI, ACM CSUR, ACM TKDD, JAIR, and DMKDJ. He also serves the community as a (senior) program committee member or reviewer of these venues. As an organiser of the anomaly and novelty detection workshop series, IJCAI-AI4AN 2020-2021 and KDD-ANDEA 2021-2022, Dr. Pang is also an Editorial Board member of IEEE Intelligent Systems and International Journal of Data Science and Analytics.
A*STAR celebrates International Women's Day
From groundbreaking discoveries to cutting-edge research, our researchers are empowering the next generation of female science, technology, engineering and mathematics (STEM) leaders.
Get inspired by our #WomeninSTEM