Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

TL;DR

This paper introduces AAL, an unsupervised few-shot learning method that generates training tasks from unlabeled data using random labels and data augmentation, enabling effective meta-learning without labels.

Contribution

The paper presents a novel approach to unsupervised few-shot learning by creating training tasks from unlabeled data through random labeling and augmentation, facilitating label-free meta-learning.

Findings

Achieves competitive performance on Omniglot and Mini-ImageNet.

Enables training of meta-learning models without any labeled data.

Demonstrates effective generalization to real-labeled few-shot tasks.

Abstract

The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set's images, and reusing the support set's labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.