Search Results for author:
Found 2 papers, 2 papers with code
Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior
This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application and increase the adaptability of prompts on unseen instances.
SAAL: Sharpness-Aware Active Learning
Specifically, our proposed method, Sharpness-Aware Active Learning (SAAL), constructs its acquisition function by selecting unlabeled instances whose perturbed loss becomes maximum.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
