Robust Meta Learning for Image based tasks

TL;DR

This paper introduces a robust meta-learning approach tailored for image-based tasks, enhancing generalization and robustness against distribution shifts and scarce data in unseen testing scenarios.

Contribution

The paper proposes a novel robust meta-learning method specifically designed to handle distribution shifts and limited data in image-based tasks, improving generalization.

Findings

Better generalization performance on unseen tasks

Robustness to distribution shifts in testing data

Effective with scarce training data

Abstract

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we learn an optimal model in training data, it could have better generalization performance in testing tasks. However, learning such a model is not possible in standard machine learning frameworks as the distribution of the test data is unknown. To tackle this challenge, we propose a novel robust meta-learning method, which is more robust to the image-based testing tasks which is unknown and has distribution shifts with training tasks. Our robust meta-learning method can provide robust optimal models even when data from each distribution are scarce. In experiments, we demonstrate that our algorithm not only has better generalization performance but also robust to different unknown testing tasks.