Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings
This addresses data-scarce learning settings, offering a potentially new standard for scenarios with limited labeled data.
The paper tackles the problem of classifying a small, unlabeled dataset with a limited labeling budget by introducing Active Few-Shot Classification (AFSC) as a new paradigm, showing gains of up to 10% in average weighted accuracy compared to state-of-the-art methods.
We consider a novel formulation of the problem of Active Few-Shot Classification (AFSC) where the objective is to classify a small, initially unlabeled, dataset given a very restrained labeling budget. This problem can be seen as a rival paradigm to classical Transductive Few-Shot Classification (TFSC), as both these approaches are applicable in similar conditions. We first propose a methodology that combines statistical inference, and an original two-tier active learning strategy that fits well into this framework. We then adapt several standard vision benchmarks from the field of TFSC. Our experiments show the potential benefits of AFSC can be substantial, with gains in average weighted accuracy of up to 10% compared to state-of-the-art TFSC methods for the same labeling budget. We believe this new paradigm could lead to new developments and standards in data-scarce learning settings.