I joined Learning and Machine Perception (LAMP) team in 2019.10 (expected to graduate at some point before 2023.10), as a PhD student advised by Dr. Joost van de Weijer in Computer Vision Center, 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 how to efficiently adapt the pretrained model to real world environment under domain and category shift unsupervisedly, where especially I work on source-free/continual/open-set/universal domain adaptation.
CV (updated Nov. 2022)
Looking for researcher/scientist position
(Tokyo, or Europe) in late 2023
News
I will be in Tokyo for about 4 months, for an internship (expectedly starting in Dec.) in OMRON SINIC X, working with Dr. Atsushi Hashimoto and Dr. Yoshitaka Ushiku on the topic of "machine learning for few training data".
[Nov. 2022] I will present our recent work on model adaptation under domain and category shift on TrustML Young Scientist Seminars (hosted by RIKEN AIP) on Dec .7.
[Sep. 2022] Our paper 'Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation' is accepted by NeurIPS 2022 as Spotlight, and paper "Positive Pair Distillation Considered Harmful: Continual Meta Metric Learning for Lifelong Object Re-Identification" is accepted by BMVC 2022.
[Jun. 2022] I will be in multiple places in Italy in July: Sicily for ICVSS summer school,
Florencefor a talk toMICClab(thanks to the strike..), Milan for the AI Symposium.[Sep. 2021] Our paper 'Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation' is accepted by NeurIPS 2021.
[Jul. 2021] Our paper 'Generalized Source-free Domain Adaptation' is accepted by ICCV 2021.
[Oct. 2018] Start working as a research associate in Kyoto University, on the topic of AI for art, working with Prof. Liang Zhao and Prof. Xuefeng Liang.
One Ring to Bring Them All: Towards Open-Set Recognition under Domain Shift
Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer
preprint
Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer
Advances in Neural Information Processing Systems (NeurIPS) 2022 Spotlight [project][paper][arXiv] [code]
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui
Advances in 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]
Research Experience
Oct. 2018~ Mar. 2019, Guest Research Associate in Kyoto University, Japan.
Invited Talks
TrustML Young Scientist Seminars, RIKEN AIP, 2022.12
AI Time Seminar on NeurIPS 2021 (Virtual), 2022.2
Academic Service
Conference Reviewer: NeurIPS 2022; ECCV 2022; ICML 2022; CVPR 2022, 2023; WACV 2021, 2022
Journal Reviewer: IEEE TKDE, TPAMI