Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
This addresses the domain generalization problem in meta-learning, which is incremental as it builds on existing frameworks to handle unseen domains.
The paper tackles the problem of meta-learning's brittleness when generalizing to unseen domains by simulating tasks from those domains to improve generalization and robustness. The result is a model-agnostic shift layer that achieves state-of-the-art performance on cross-domain few-shot classification benchmarks and good results on regression tasks.
Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to generalize to tasks from the other unseen domains. In this work, we address this problem by simulating tasks from the other unseen domains to improve the generalization and robustness of meta-learning method. Specifically, we propose a model-agnostic shift layer to learn how to simulate the domain shift and generate pseudo tasks, and develop a new adversarial learning-to-learn mechanism to train it. Based on the pseudo tasks, the meta-learning model can learn cross-domain meta-knowledge, which can generalize well on unseen domains. We conduct extensive experiments under the domain generalization setting. Experimental results demonstrate that the proposed shift layer is applicable to various meta-learning frameworks. Moreover, our method also leads to state-of-the-art performance on different cross-domain few-shot classification benchmarks and produces good results on cross-domain few-shot regression.