Research Interests

• Machine Learning
• Computer Vision
• Vision-Language
• Few-shot Learning
• Visual Reasoning

Work Experience

• (2021 - Present) Research Assistant, AI Lab, Sustech, Shenzhen
• (2020 - 2021) Lecture, Neusoft Institute Guangdong, Foshan
• (2018 - 2020) Software Engineer, SAP, Shanghai
• (2016 - 2018) Software Engineer, The University of Southern Mississippi

Paper

• Yi Zhang, Ce Zhang, Ke Yu, Yushun Tang, Zhihai He. Concept-Guided Prompt Learning for Generalization in Vision-Language Models. AAAI2024.
• Yi Zhang, Ce Zhang, Zihan Liao, Yushun Tang, Zhihai He. BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning. British Machine Vision Conference 2023 (BMVC2023).
• Xueting Hu, Ce Zhang, Yi Zhang, Ke Yu, Zhihai He. Learn to Adapt CLIP for Few-Shot Monocular Depth Estimation. Submitted to Winter Conference on Computer Vision (WACV), 2024. (Project Lead)
• Yi Zhang, Ce Zhang, Xueting Hu, Zhihai He. Unsupervised Prototype Adapter for Vision-Language Models. The 6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV2023).
• Yi Zhang, Ce Zhang, Yushun Tang, Zhihai He. Cross-Model concept learning and reference for Vision-Language Models. Neurocomputing. (Under review)
• Yi Zhang, Ce Zhang, Zhihai He. Distribution Learning Adapter for Vision-Language Models. (Preprint)
• Yushun Tang, Shuoshuo Chen, Zhehan Kan, Yi Zhang, Qinghai Guo, Zhihai He. Learning Visual Conditioning Tokens to Clean Up Domain Shift for Fully Test-Time Adaptation. IEEE Transactions on Circuits and Systems for Video Technology(TCSVT) (Under review)