Open Domain Generalization with Domain-Augmented Meta-Learning

04/08/2021
by   Yang Shu, et al.
0

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.

READ FULL TEXT
research
12/01/2020

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Recent advances in person re-identification (ReID) obtain impressive acc...
research
08/18/2023

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

Domain generalization (DG) is proposed to deal with the issue of domain ...
research
10/22/2020

Meta-Learning for Domain Generalization in Semantic Parsing

The importance of building semantic parsers which can be applied to new ...
research
03/24/2022

Compound Domain Generalization via Meta-Knowledge Encoding

Domain generalization (DG) aims to improve the generalization performanc...
research
03/31/2023

Simple Domain Generalization Methods are Strong Baselines for Open Domain Generalization

In real-world applications, a machine learning model is required to hand...
research
06/01/2023

Domain Generalization for Domain-Linked Classes

Domain generalization (DG) focuses on transferring domain-invariant know...
research
10/25/2022

Learning to Augment via Implicit Differentiation for Domain Generalization

Machine learning models are intrinsically vulnerable to domain shift bet...

Please sign up or login with your details

Forgot password? Click here to reset