AQFC2015

Research on Cross-Domain Semantic Segmentation

----------------------------------------------------------------------------------------------------

    Department of Systems Engineering and Engineering Management

                       The Chinese University of Hong Kong

----------------------------------------------------------------------------------------------------

Date: Thursday, August 10, 2023, 04:30pm HKT

Venue: ERB 513, The Chinese University of Hong Kong

Title: Research on Cross-Domain Semantic Segmentation

Speaker: Prof. Shuang Wang, Xidian University, Senior Member of IEEE

 

Abstract:

Deep learning techniques have significantly improved the performances of many computer visual applications. However, existing deep learning models are usually constrained by a closed-domain assumption. They will exhibit significant performance degradation in the open domains, which severely limits the application of deep learning in open environments. This report will introduce the development and applications of semantic segmentation in an open environment, as well as the research of our group in recent years, including domain alignment of structural transfer, multi-domain adaptation of co-evolution, model adaptation in privacy scenarios (source-free domain adaptation), etc.

 

Biography:

Shuang Wang, Senior Member, IEEE. She is a professor at the Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, Xidian University. Her research interests include deep learning, intelligent information processing, multimodal learning, semantic segmentation, etc.

Professor Wang has published about 80 papers, and the Google citation is 3000+. Her many research works have been published in journals of IEEE Transactions on Image Processing (IEEE TIP), IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS), ISPRS Journal of Photogrammetry and Remote Sensing (ISPRS) and CCF-A conferences of IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) and International Conference on Computer Vision (ICCV).

Professor Wang also guides students acquired many international competition awards, such as the 2018/2022 IEEE GRSS Data Fusion Contest, the 2022 CVPR Agriculture-vision Cropharvest challenge, and the 2022 IJCAI-ECAI Landslide4Sense competition.

 

Everyone is welcome to attend the talk!

SEEM-5201 Website: http://seminar.se.cuhk.edu.hk

Email: seem5201@se.cuhk.edu.hk

 

Date: 
Thursday, August 10, 2023 - 16:30