Few Shot Learning With No Labels

TL;DR

This paper introduces a zero-label few-shot learning approach that leverages self-supervised learning and image similarity, enabling recognition of new categories without any labeled data during training or testing.

Contribution

It proposes a novel setting for few-shot learning with no label access, using self-supervision and similarity measures to achieve competitive results.

Findings

Achieves competitive performance with zero labels

Reduces reliance on annotated data

Presents a new challenging setting for few-shot learning

Abstract

Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes use of vast amounts of annotated data by simply shifting the label requirement from novel classes to base classes. Since data annotation is time-consuming and costly, reducing the label requirement even further is an important goal. To that end, our paper presents a more challenging few-shot setting where no label access is allowed during training or testing. By leveraging self-supervision for learning image representations and image similarity for classification at test time, we achieve competitive baselines while using \textbf{zero} labels, which is at least fewer labels than state-of-the-art. We hope that this work is a step towards developing few-shot learning methods which do not depend on annotated data at all. Our code will be publicly released.