↓Skip to main content

🏢 University of New South Wales (UNSW Sydney)

CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
·3973 words·19 mins· loading · loading
Multimodal Learning Vision-Language Models 🏢 University of New South Wales (UNSW Sydney)
CLAP4CLIP enhances vision-language model continual learning by using probabilistic finetuning, improving performance and uncertainty estimation.