Shiqi Yang

Ph.D Candidate

syang@cvc.uab.es

I joined Learning and Machine Perception (LAMP) team in 2019.10, as a Ph.D student advised by Dr. Joost van de Weijer in Computer Vision Center of Autonomous University of Barcelona, Spain. I received Master degree from the Huazhong University of Science and Technology, China in 2019, during my master study I once worked as research associate in Kyoto University, Japan. My research interest focuses on computer vision and deep learning, where especially I work on source-free domain adaptation. Currently, I am also stepping into reinforcement learning.

CV

Looking for summer Research Intern 2022 (both academic and industrial)!

News

Publications

arXiv

  • Unsupervised Domain Adaptation without Source Data by Casting a BAIT

Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui

[arxiv] [code]


International Conference

  • Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation

Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui

Conference on Neural Information Processing Systems (NeurIPS) 2021 [project] [paper] [arXiv] [code] [video]

  • Generalized Source-free Domain Adaptation

Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui

International Conference on Computer Vision (ICCV) 2021 [project] [paper] [arXiv] [code] [video]

  • Parallel Convolutional Networks for Image Recognition via a Discriminator

Shiqi Yang, Gang Peng

Asian Conference on Computer Vision (ACCV) 2018 [paper] [arXiv]

  • Attention to Refine Through Multi Scales for Semantic Segmentation

Shiqi Yang, Gang Peng

Pacific-Rim Conference on Multimedia (PCM) 2018 [paper] [arXiv]


Journal

  • On Implicit Attribute Localization for Generalized Zero-Shot Learning

Shiqi Yang, Kai Wang, Luis Herranz, Joost van de Weijer

IEEE Signal Processing Letters, 2021 [paper] [arXiv]

Research Experience

  • Oct. 2018~ Mar. 2019, Guest Research Associate in Kyoto University, Japan.

Academic Service

Conference Reviewer: CVPR 2022; WACV 2021, 2022