← Search

Mengyu Zheng*

2 accepted papers

2024

Adapt without Forgetting: Distill Proximity from Dual Teachers in Vision-Language Models

ECCV 2024poster

"Multi-modal models such as CLIP possess remarkable zero-shot transfer capabilities, making them highly effective in continual learning tasks. However, this advantage is severely compromised by catastrophic forgetting, which undermines the valuable zero-shot learning abilities of these models. Exist…