no code implementations • 2 Aug 2023 • Zixuan Ni, Longhui Wei, Jiacheng Li, Siliang Tang, Yueting Zhuang, Qi Tian
In this work, we propose a novel strategy named \textbf{Degeneration-Tuning (DT)} to shield contents of unwanted concepts from SD weights.
no code implementations • 11 May 2023 • Zixuan Ni, Longhui Wei, Siliang Tang, Yueting Zhuang, Qi Tian
Moreover, we empirically and theoretically demonstrate how SD leads to a performance decline for CLIP on cross-modal retrieval tasks.
no code implementations • 18 Nov 2021 • Zixuan Ni, Siliang Tang, Yueting Zhuang
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels.
no code implementations • 26 Jul 2021 • Zixuan Ni, Haizhou Shi, Siliang Tang, Longhui Wei, Qi Tian, Yueting Zhuang
After investigating existing strategies, we observe that there is a lack of study on how to prevent the inter-phase confusion.