Unsupervised Meta-Learning For Few-Shot Image Classification

TL;DR

UMTRA is an unsupervised, model-agnostic meta-learning algorithm that creates synthetic tasks from unlabeled images to enable few-shot classification, reducing label dependence while maintaining competitive performance.

Contribution

It introduces UMTRA, a novel unsupervised meta-learning method that requires minimal labeling, using data augmentation and random sampling to generate training tasks.

Findings

UMTRA outperforms existing unsupervised methods on Omniglot and Mini-ImageNet.

UMTRA achieves competitive results with significantly fewer labels than supervised approaches.

UMTRA's performance is comparable to recent algorithms like CACTUs.

Abstract

Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. In this paper, we propose UMTRA, an algorithm that performs unsupervised, model-agnostic meta-learning for classification tasks. The meta-learning step of UMTRA is performed on a flat collection of unlabeled images. While we assume that these images can be grouped into a diverse set of classes and are relevant to the target task, no explicit information about the classes or any labels are needed. UMTRA uses random sampling and augmentation to create synthetic training tasks for meta-learning phase. Labels are only needed at the final target task learning step, and they can be as little as one sample per class. On the Omniglot and Mini-Imagenet few-shot learning benchmarks, UMTRA outperforms every tested approach based on unsupervised learning of representations, while alternating for the best performance with the recent CACTUs algorithm. Compared to supervised model-agnostic meta-learning approaches, UMTRA trades off some classification accuracy for a reduction in the required labels of several orders of magnitude.