mayug/VDT-Adapter
This repository contains the code and datasets for our ICCV-W paper 'Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Prompts'
ShellMIT
Issues
- 0
kindly request reproducible prompts
#3 opened - 1
csv for CUB split
#2 opened - 1
The GPT-4 generated dataset
#1 opened