Diffusion-based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection

Out-of-distribution (OOD) detection, determining whether a given sample is part of the in-distribution (ID) or not, has been newly explored by a generative model-based outlier synthesizing approach, especially with diffusion models. Nonetheless, existing diffusion models often produce outliers that are considerably distant from the ID in pixel-space, showing limited efficacy for capturing subtle distinctions between ID and OOD. To address these issues, we propose a novel framework, Semantic Outlier generation via Nuisance Awareness (SONA), which directly utilizes informative pixel-space ID images in diffusion models. Thereby, the generated outliers achieve two crucial properties: (i) they closely resemble the ID mainly in nuisances, while (ii) represent discriminative semantic information. To facilitate the separate effect on semantics and nuisances, we introduce SONA guidance, providing region-specific guidance. Extensive experiments demonstrate the effectiveness of our framework, achieving an impressive AUROC of 87% on near-OOD datasets, which surpasses the performance of baseline methods by a significant margin of approximately 6%.

Authors

• Suhee Yoon LG AI Research
• Sanghyu Yoon LG AI Research
• Ye Seul Sim LG AI Research
• Sungik Choi LG AI Research
• Kyungeun Lee LG AI Research
• Hye-Seung Cho LG AI Research
• Hankook Lee Sungkyunkwan University
• Woohyung Lim LG AI Research

Keywords

No keywords are indexed for this paper.