Out-of-distribution (OOD) detection is vital for ensuring the safety and reliability of artificial intelligence systems. It represents a novel and trending area in machine learning and artificial intelligence. The concept of OOD detection was first proposed in 2017 and has since shown significant potential in enabling the reliable deployment of machine learning models in real-world applications, including medical safety and autonomous driving system. Over the past few years, a rich line of algorithms has been developed to address the generalized OOD detection problem empirically. In this talk, we will present the latest advancements in OOD detection theory, and OOD detection algorithms.
Speaker Bio
Dr Zhen Fang is currently a Lecturer (Research) at the Australian Artificial Intelligence Institute, University of Technology Sydney (UTS), working with Prof. Jie Lu. He received his Ph.D degree in artificial intelligence from UTS (2018-2022), supervised by Prof. Jie Lu. His research interests include transfer learning, statistical learning theory and out-of-distribution learning, and his works have been published in top AI journals and AI conferences e.g., NeurIPS, ICML and IEEE-TPAMI. Recently, Zhen also received the Outstanding Paper Award in NeurIPS 2022 for his work related to out-of-distribution detection theory.
More Details
- When: Wed 23 Aug 2023, at 1:00 pm (GMT+10)
- Speaker: Dr Zhen Fang (University of Technology Sydney)
- Host: Dr Yadan Luo
- Zoom: https://uqz.zoom.us/j/82896549343
No.23-15 How to Detect Out-of-Distribution Data in the Wild? Challenges, Research Progress and Path Forward