A Focus on Important Samples for Out-of-Distribution Detection

Jiaqi Wan, Guoliang Wen, Guangming Sun, Yuntian Zhu and Zhaohui Hu ()
Additional contact information
Jiaqi Wan: College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
Guoliang Wen: College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
Guangming Sun: College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
Yuntian Zhu: College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China
Zhaohui Hu: College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China

Mathematics, 2025, vol. 13, issue 12, 1-15

Abstract: To ensure the reliability and security of machine learning classification models when deployed in the open world, it is crucial that these models can detect out-of-distribution (OOD) data that exhibits semantic shifts from the in-distribution (ID) data used during training. This necessity has spurred extensive research on OOD detection. Previous methods required a large amount of finely labeled OOD data for model training, which is costly or performed poorly in open-world scenarios. To address these limitations, we propose a novel method named focus on important samples (FIS) in this paper. FIS leverages model-predicted OOD scores to identify and focus on important samples that are more beneficial for model training. By learning from these important samples, our method aims to achieve reliable OOD detection performance while reducing training costs and the risk of overfitting training data, thereby enabling the model to better distinguish between ID and OOD data. Extensive experiments across diverse OOD detection scenarios demonstrate that FIS achieves superior performance compared to existing approaches, highlighting its robust and efficient OOD detection performance in practical applications.

Keywords: out-of-distribution detection; reliable machine learning; active learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/12/1998/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/12/1998/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:12:p:1998-:d:1680870

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().