I joined Learning and Machine Perception (LAMP) team in 2019.10 as a PhD student (~ to defend in early July 2023), advised by Dr. Joost van de Weijer in Computer Vision Center, Autonomous University of Barcelona, Spain. My research during PhD focuses on how to efficiently adapt the pretrained model to real world environment (on computer vision tasks) under domain and category shift unsupervisedly, such as source-free/continual/open-set/universal domain adaptation. Currently I am interested in utilizing pre-trained multi-modal models for downstream recognition tasks.
CV (updated Apr. 2023)
Currently I am interning in OMRON SINIC X Tokyo, on open-vocabulary segmentation with StableDiffusion
News
[2023.4] Receive research grant (HPC support) from StabilityAI for my internship project.
[2023.1] Nice to visit Prof. Maria Brbic's group in EPFL. And I start the internship in OMRON SINIC X Tokyo, working with Dr. Atsushi Hashimoto and Dr. Yoshitaka Ushiku on Open-Vocabulary Semantic Segmentation with pretrained CLIP/StableDiffusion.
[2022.11] I will present our work on model adaptation under domain and category shift on TrustML Young Scientist Seminars (hosted by RIKEN AIP) on Dec .7.
[2022.9] 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.
[2022.6] I will be in multiple places in Italy in July: Sicily for ICVSS summer school, Florence for a talk to MICC lab (thanks to the strike..), Milan for the AI Symposium.
[2021.9] Our paper 'Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation' is accepted by NeurIPS 2021.
[2021.7] Our paper 'Generalized Source-free Domain Adaptation' is accepted by ICCV 2021.
[2018.10] Start research associate in Kyoto University, on image generation/translation for artwork, working with Prof. Liang Zhao and Prof. Xuefeng Liang.
OneRing: A Simple Method for Source-free Open-partial Domain Adaptation
Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost van de Weijer
preprint, under reviewing
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]