Publications

International Conference

Make Prompts Adaptable : Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior
categorize
Machine Learning
Author
Youngjae Cho, HeeSun Bae, Seungjae Shin, YeoDong Youn, Weonyoung Joo, and Il-Chul Moon
Year
2024
Conference Name
AAAI Conference on Artificial Intelligence (AAAI 2024)
Presentation Date
Feb 22-25
City
Vancouver
Country
Canada

Youngjae Cho, HeeSun Bae, Seungjae Shin, YeoDong Youn, Weonyoung Joo, and Il-Chul Moon, Make Prompts Adaptable : Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior, AAAI Conference on Artificial Intelligence (AAAI 2024), Vancouver, Canada, Feb 22-25, 2024 


Abstract

Recent Vision-Language Pretrained (VLP) models have become the backbone for many downstream tasks, but they are utilized as frozen model without learning. Prompt learning is a method to improve the pre-trained VLP model by adding a learnable context vector to the inputs of the text encoder. In a few-shot learning scenario of the downstream task, MLE training can lead the context vector to over-fit dominant image features in the training data. This overfitting can potentially harm the generalization ability, especially in the presence of a distribution shift between the training and test dataset. 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. Specifically, modeling data-dependent prior enhances the adaptability of text features for both seen and unseen image features without the trade-off of performance between them. Based on the Bayesian framework, we utilize the Wasserstein Gradient Flow in the estimation of our target posterior distribution, which enables our prompt to be flexible in capturing the complex modes of image features. We demonstrate the effectiveness of our method on benchmark datasets for several experiments by showing statistically significant improvements on performance compared to existing methods. The code is available at https://github.com/youngjae-cho/APP.


@article{cho2024make, 

title={Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior}, 

author={Cho, Youngjae and Bae, HeeSun and Shin, Seungjae and Youn, Yeo Dong and Joo, Weonyoung and Moon, Il-Chul}, 

journal={arXiv preprint arXiv:2401.06799}, 

year={2024} 

}


Source Website:

https://arxiv.org/abs/2401.06799