Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

TL;DR

This paper introduces an unsupervised method for selecting the most representative and diverse data points to label, significantly enhancing semi-supervised learning efficiency especially with limited annotation budgets.

Contribution

It proposes an unsupervised approach to select data for labeling that improves SSL performance without requiring labeled data for selection.

Findings

Consistently outperforms state-of-the-art active learning methods

Boosts FixMatch accuracy by 10-14% with minimal labeled data

Achieves 8-25 times better label efficiency

Abstract

Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right data to label, in addition to usual SSL's propagating labels from labeled data to the rest unlabeled data. This instance selection task is challenging, as without any labeled data we do not know what the objective of learning should be. Intuitively, no matter what the downstream task is, instances to be labeled must be representative and diverse: The former would facilitate label propagation to unlabeled data, whereas the latter would ensure coverage of the entire dataset. We capture this idea by selecting cluster prototypes, either in a pretrained feature space, or along with feature optimization, both without labels. Our unsupervised selective labeling consistently improves SSL methods over state-of-the-art active learning given labeled data, by 8 to 25 times in label efficiency. For example, it boosts FixMatch by 10% (14%) in accuracy on CIFAR-10 (ImageNet-1K) with 0.08% (0.2%) labeled data, demonstrating that small computation spent on selecting what data to label brings significant gain especially under a low annotation budget. Our work sets a new standard for practical and efficient SSL.