Learning From Hard Negative Samples: Multi-Prototype Contrastive Learning for Out-of-Distribution Detection
IEEE Access · 2026 · 14 · 84797-84808
DOI: 10.1109/access.2026.3699706 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Jinhyuk Suh und 1 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Institute of Information and Communications Technology Planning and Evaluation (IITP) grant, Korean Government (MSIT), XVoice: Multi-Modal Voice Meta Learning, National Research Foundation of Korea (NRF) grant.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Institute of Information and Communications Technology Planning and Evaluation (IITP) grant
- Korean Government (MSIT), XVoice: Multi-Modal Voice Meta Learning
- National Research Foundation of Korea (NRF) grant
- Korean Government
Zitieren
APA
Suh, J., & Hur, Y. (2026). Learning From Hard Negative Samples: Multi-Prototype Contrastive Learning for Out-of-Distribution Detection. IEEE Access, 14, 84797-84808. https://doi.org/10.1109/access.2026.3699706
Vancouver
Suh J, Hur Y. Learning From Hard Negative Samples: Multi-Prototype Contrastive Learning for Out-of-Distribution Detection. IEEE Access. 2026;14:84797-84808. doi:10.1109/access.2026.3699706
BibTeX
@article{Suh2026,
author = {Suh, Jinhyuk and Hur, Youngbum},
title = {Learning From Hard Negative Samples: Multi-Prototype Contrastive Learning for Out-of-Distribution Detection},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {84797--84808},
doi = {10.1109/access.2026.3699706}
}
EUVIMED