Colloquiums and Conferences
A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation
Time: 2025-12-16 19:15:00
Title: A Novel Wasserstein Quaternion Generative Adversarial Network for Color Image Generation
Speaker: Prof. Zhigang Jia (Invited by Prof. Xiaofei Peng)
Affiliation: Jiangsu Normal University
Time: December 16, 15:30–16:30
Venue: Room 401, East Building, School of Mathematical Sciences
Speaker Biography:
Zhigang Jia is a professor and doctoral supervisor in the School of Mathematics and Statistics and the Institute of Mathematics at Jiangsu Normal University. He received his Ph.D. in mathematics from East China Normal University in 2009. In 2023 he was selected as a young and middle-aged academic leader under the Jiangsu Qinglan Project, and since 2024 he has served on the editorial board of Numerical Algorithms. His research interests include numerical algebra and image processing. He has published more than 50 papers in journals such as IEEE Transactions on Image Processing, SIAM Journal on Matrix Analysis and Applications, SIAM Journal on Scientific Computing and SIAM Journal on Imaging Sciences, two of which are ESI highly cited papers, and has authored an English monograph published by Science Press (Beijing). He has led three projects funded by the National Natural Science Foundation of China and one major project of the Jiangsu Provincial University Natural Science Research Programme, and has participated in a major NSFC project and a National Key R&D Programme project. He has received first prize of the 10th Huaihai Science and Technology Award and third prize of the Jiangsu Provincial University Science and Technology Research Award, and has visited the University of Manchester, Hong Kong Baptist University and the University of Macau.
Abstract:
Color image generation has a wide range of applications, but the existing generation models ignore the correlation among color channels, which may lead to chromatic aberration problems. In addition, the data distribution problem of color images has not been systematically elaborated and explained, so that there is still the lack of the theory about measuring different color images datasets. In this talk, we define a new quaternion Wasserstein distance and develop its dual theory. To deal with the quaternion linear programming problem, we derive the strong duality form with helps of quaternion convex set separation theorem and quaternion Farkas lemma. With using quaternion Wasserstein distance, we propose a novel Wasserstein quaternion generative adversarial network. Experiments demonstrate that this novel model surpasses both the (quaternion) generative adversarial networks and the Wasserstein generative adversarial network in terms of generation efficiency and image quality.