.png?sfvrsn=d3a97fa3_9)
Data-centric Computer Vision
[CFAR Rising Star Lecture Series]
Data-centric Computer Vision by Dr Liang Zheng
Computer vision research depends heavily on data and model. While the latter has been extensive designed and studied, the definition and analysis of problems associated data are still less well understood.
In this talk, Dr Liang Zheng will introduce his group’s attempts that focus on the properties of training data, validation data, and test data, followed by the methods on improving the quality of training data and validation data for better models to be trained or selected. He will also talk about ways to evaluate the difficulty of the test data, or in other words, the model accuracy, in an unsupervised way. Dr Liang will then conclude the talk by sharing his perspectives on data-centric problems and its un-addressed challenges.
Data-centric Computer Vision by Dr Liang Zheng
6 Feb 2023 | 3.00pm (Singapore Time)
Computer vision research depends heavily on data and model. While the latter has been extensive designed and studied, the definition and analysis of problems associated data are still less well understood.
In this talk, Dr Liang Zheng will introduce his group’s attempts that focus on the properties of training data, validation data, and test data, followed by the methods on improving the quality of training data and validation data for better models to be trained or selected. He will also talk about ways to evaluate the difficulty of the test data, or in other words, the model accuracy, in an unsupervised way. Dr Liang will then conclude the talk by sharing his perspectives on data-centric problems and its un-addressed challenges.
SPEAKER
Dr Liang Zheng
Senior Lecturer
Australian National University
Senior Lecturer
Australian National University
Dr Liang Zheng is a Senior Lecturer in the Australian National University and best known for his contributions in object re-identification. Together with his collaborators, he designed widely used datasets and algorithms such as Market-1501 (ICCV 2015), part-based convolutional baseline (ECCV 2018), random erasing (AAAI 2020) and joint detection and embedding (ECCV 2020). His recent research interest centers around data-centric computer vision, with primary focus on improving, leveraging and analysing data instead of algorithms. He was/is a co-organiser of the AI City workshop series and the Vision Datasets Understanding workshops at CVPR. Besides serving as an Area Chair for important conferences such as CVPR, ICCV and ECCV, Dr Liang is also an Associate Editor for IEEE Transactions on Circuits and Systems for Video Technology. He received his B.S degree and Ph.D degree from Tsinghua University, China in 2010 and 2015 respectively.
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