Dynamic Domain Generalization

TL;DR

This paper introduces Dynamic Domain Generalization (DDG), a novel approach that enables models to adapt to unseen domains by dynamically twisting network parameters using a meta-adjuster, without retraining.

Contribution

The paper proposes a new DDG framework that dynamically adjusts model parameters for unseen domains, combining static domain-invariant learning with a meta-adjuster for domain-specific adaptation.

Findings

DDG outperforms existing domain generalization methods in experiments.

The meta-adjuster effectively adapts models to diverse unseen domains.

DomainMix enhances the training process by simulating multiple domains.

Abstract

Domain generalization (DG) is a fundamental yet very challenging research topic in machine learning. The existing arts mainly focus on learning domain-invariant features with limited source domains in a static model. Unfortunately, there is a lack of training-free mechanism to adjust the model when generalized to the agnostic target domains. To tackle this problem, we develop a brand-new DG variant, namely Dynamic Domain Generalization (DDG), in which the model learns to twist the network parameters to adapt the data from different domains. Specifically, we leverage a meta-adjuster to twist the network parameters based on the static model with respect to different data from different domains. In this way, the static model is optimized to learn domain-shared features, while the meta-adjuster is designed to learn domain-specific features. To enable this process, DomainMix is exploited to simulate data from diverse domains during teaching the meta-adjuster to adapt to the upcoming agnostic target domains. This learning mechanism urges the model to generalize to different agnostic target domains via adjusting the model without training. Extensive experiments demonstrate the effectiveness of our proposed method. Code is available at: https://github.com/MetaVisionLab/DDG