An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learning
This addresses the problem of limited labeled data in few-shot learning for AI practitioners, though it is incremental as it builds on existing methods with a simpler approach.
The paper tackles semi-supervised few-shot learning by proposing a simple method to predict negative pseudo-labels from unlabeled data and augment the support set, achieving state-of-the-art performance on four benchmark datasets.
Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this problem comprises. In this paper, we propose a simple but quite effective approach to predict accurate negative pseudo-labels of unlabeled data from an indirect learning perspective, and then augment the extremely label-constrained support set in few-shot classification tasks. Our approach can be implemented in just few lines of code by only using off-the-shelf operations, yet it is able to outperform state-of-the-art methods on four benchmark datasets.