Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn

TL;DR

Meta Omnium is a comprehensive benchmark dataset designed to evaluate the ability of meta-learning algorithms to generalize across diverse vision tasks such as recognition, segmentation, and regression.

Contribution

The paper introduces Meta Omnium, a new dataset-of-datasets that enables evaluation of meta-learning models across multiple vision tasks in a unified framework.

Findings

Meta-learning models show limited cross-task generalization.

Meta Omnium facilitates comprehensive evaluation of meta-learners.

Baseline experiments reveal challenges in transferability across tasks.

Abstract

Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction. This naturally raises the question of whether there is any few-shot meta-learning algorithm capable of generalizing across these diverse task types? To support the community in answering this question, we introduce Meta Omnium, a dataset-of-datasets spanning multiple vision tasks including recognition, keypoint localization, semantic segmentation and regression. We experiment with popular few-shot meta-learning baselines and analyze their ability to generalize across tasks and to transfer knowledge between them. Meta Omnium enables meta-learning researchers to evaluate model generalization to a much wider array of tasks than previously possible, and provides a single framework for evaluating meta-learners across a wide suite of vision applications in a consistent manner.