Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalization

TL;DR

This paper introduces a unified framework called Feature-space Semantic Invariance (FSI) that improves open-set domain generalization by maintaining semantic consistency across domains and using generative models to enhance robustness, leading to better OOD detection and classification accuracy.

Contribution

The paper proposes FSI, a novel approach that unifies open-set domain generalization and OOD detection by preserving semantic invariance in feature space and leveraging generative models for data augmentation.

Findings

Improves AUROC by 9.1% to 18.9% on ColoredMNIST.

Enhances model robustness and in-distribution classification accuracy.

Provides a unified framework for open-set domain generalization and OOD detection.

Abstract

Open-set domain generalization addresses a real-world challenge: training a model to generalize across unseen domains (domain generalization) while also detecting samples from unknown classes not encountered during training (open-set recognition). However, most existing approaches tackle these issues separately, limiting their practical applicability. To overcome this limitation, we propose a unified framework for open-set domain generalization by introducing Feature-space Semantic Invariance (FSI). FSI maintains semantic consistency across different domains within the feature space, enabling more accurate detection of OOD instances in unseen domains. Additionally, we adopt a generative model to produce synthetic data with novel domain styles or class labels, enhancing model robustness. Initial experiments show that our method improves AUROC by 9.1% to 18.9% on ColoredMNIST, while also significantly increasing in-distribution classification accuracy.