Prompt-driven Zero-shot Domain Adaptation
2 papers with code • 0 benchmarks • 0 datasets
Domain adaptation using only a single source domain and a description of the target domain in natural language (No images from target domain are available)
Benchmarks
These leaderboards are used to track progress in Prompt-driven Zero-shot Domain Adaptation
Most implemented papers
PØDA: Prompt-driven Zero-shot Domain Adaptation
In this paper, we propose the task of `Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
PODA: Prompt-driven Zero-shot Domain Adaptation
astra-vision/poda
•
•
ICCV 2023
In this paper, we propose the task of 'Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
