← Search

Yunlong Yu*

2 accepted papers

2024

Improving Zero-Shot Generalization for CLIP with Variational Adapter

ECCV 2024poster

"The excellent generalization capability of pre-trained Vision-Language Models (VLMs) makes fine-tuning VLMs for downstream zero-shot tasks a popular choice. Despite achieving promising performance in the professionality of base classes, most existing fine-tuned methods suffer from feature confusion…

Cited by 8SourcePDFScholar
2024

RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-based Continual Learning

ECCV 2024poster

"Prompt-based Continual Learning is an emerging direction in leveraging pre-trained knowledge for downstream continual learning. While arriving at a new session, existing prompt-based continual learning methods usually adapt features from pre-trained models to new data by introducing prompts. Howeve…