Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective
This addresses the challenge of OOD detection in unseen domains for machine learning systems, though it appears incremental as it builds on existing domain generalization and OOD detection techniques.
The paper tackles the problem of semantic out-of-distribution (OOD) detection across domains, addressing both covariate and semantic shifts simultaneously, and shows superiority over conventional domain generalization approaches in OOD detection performance on three benchmarks while maintaining comparable in-distribution classification accuracy.
Two prevalent types of distributional shifts in machine learning are the covariate shift (as observed across different domains) and the semantic shift (as seen across different classes). Traditional OOD detection techniques typically address only one of these shifts. However, real-world testing environments often present a combination of both covariate and semantic shifts. In this study, we introduce a novel problem, semantic OOD detection across domains, which simultaneously addresses both distributional shifts. To this end, we introduce two regularization strategies: domain generalization regularization, which ensures semantic invariance across domains to counteract the covariate shift, and OOD detection regularization, designed to enhance OOD detection capabilities against the semantic shift through energy bounding. Through rigorous testing on three standard domain generalization benchmarks, our proposed framework showcases its superiority over conventional domain generalization approaches in terms of OOD detection performance. Moreover, it holds its ground by maintaining comparable InD classification accuracy.