Policy Gradient-Based Optimal Subset Selection for Few-Shot Vision-Language Learning
Ali, Muhammad Khizer Paul, Manoranjan Ulhaq, Anwaar Khan, Muhammad Haris Mamun, Quazi
Ali, Muhammad Khizer
Paul, Manoranjan
Ulhaq, Anwaar
Khan, Muhammad Haris
Mamun, Quazi
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Vision-Language models (VLMs) like Contrastive Language-Image Pre-Training (CLIP) have been extensively adapted for few-shot classification. Most few-shot methods rely on randomly selected samples from the dataset. However, since only a few samples are used, the sample selection process can significantly impact the performance of the downstream classification task. In this work, we propose a reinforcement learning-based policy gradient technique that employs a diversity and informativeness-based reward function to optimise the sample selection process. We evaluate various sample selection techniques based on downstream classification accuracy across three benchmark datasets, where the proposed method demonstrates promising results.
Citation
M. K. Ali, M. Paul, A. Ulhaq, M. H. Khan and Q. Mamun, "Policy Gradient-Based Optimal Subset Selection for Few-Shot Vision-Language Learning," 2025 IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, 2025, pp. 1510-1515, doi: 10.1109/ICIP55913.2025.11084464.
Source
Proceedings of IEEE International Conference on Image Processing
Conference
2025 IEEE International Conference on Image Processing (ICIP)
Keywords
Sample Selection, Few-Shot Learning, Vision Language Models
Subjects
Source
2025 IEEE International Conference on Image Processing (ICIP)
Publisher
IEEE