Parameter-Efficient Active Learning for Foundational models
This work addresses efficient data annotation in specialized domains with limited budgets, though it appears incremental as it combines existing techniques rather than introducing fundamentally new approaches.
The researchers tackled the problem of improving active learning sampling selection for budget-constrained image classification tasks by combining parameter-efficient fine-tuning methods with foundational vision transformer models, demonstrating improved performance on challenging out-of-distribution datasets.
Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning (AL) framework, to advance the sampling selection process in extremely budget constrained classification tasks. The focus on image datasets, known for their out-of-distribution characteristics, adds a layer of complexity and relevance to our study. Through a detailed evaluation, we illustrate the improved AL performance on these challenging datasets, highlighting the strategic advantage of merging parameter efficient fine tuning methods with foundation models. This contributes to the broader discourse on optimizing AL strategies, presenting a promising avenue for future exploration in leveraging foundation models for efficient and effective data annotation in specialized domains.