Open Domain Generalization with Domain-Augmented Meta-Learning

Abstract

Leveraging datasets available to learn a model with high generalization ability to unseen domains is important for computer vision, especially when the unseen domain's annotated data are unavailable. We study a novel and practical problem of Open Domain Generalization (OpenDG), which learns from different source domains to achieve high performance on an unknown target domain, where the distributions and label sets of each individual source domain and the target domain can be different. The problem can be generally applied to diverse source domains and widely applicable to real-world applications. We propose a Domain-Augmented Meta-Learning framework to learn open-domain generalizable representations. We augment domains on both feature-level by a new Dirichlet mixup and label-level by distilled soft-labeling, which complements each domain with missing classes and other domain knowledge. We conduct meta-learning over domains by designing new meta-learning tasks and losses to preserve domain unique knowledge and generalize knowledge across domains simultaneously. Experiment results on various multi-domain datasets demonstrate that the proposed Domain-Augmented Meta-Learning (DAML) outperforms prior methods for unseen domain recognition.

References in corpus (10)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Learning Transferable Features with Deep Adaptation Networks
• Improved Regularization of Convolutional Neural Networks with Cutout
• Domain Generalization via Invariant Feature Representation
• VisDA: The Visual Domain Adaptation Challenge
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Heterogeneous Domain Generalization via Domain Mixup
• APAC: Augmented PAttern Classification with Neural Networks
• Feature-Critic Networks for Heterogeneous Domain Generalization
• Self-Challenging Improves Cross-Domain Generalization