Revisiting the training of generative adversarial networks via non-leaking rotational data augmentation
Pattern Analysis and Applications · 2026-12 · 29 (4)
DOI: 10.1007/s10044-026-01809-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Pattern Analysis and Applications, online erschienen am 12.11.2026. Verfasst von Kensuke Nakamura und 3 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Gefördert von: Artificial Intelligence Graduate School, Chung-Ang University, National Research Foundation of Korea.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Artificial Intelligence Graduate School, Chung-Ang University
- National Research Foundation of Korea
Zitieren
APA
Nakamura, K., Sohn, B., Korman, S., & Hong, B. (2026). Revisiting the training of generative adversarial networks via non-leaking rotational data augmentation. Pattern Analysis and Applications, 29(4). https://doi.org/10.1007/s10044-026-01809-6
Vancouver
Nakamura K, Sohn B, Korman S, Hong B. Revisiting the training of generative adversarial networks via non-leaking rotational data augmentation. Pattern Analysis and Applications. 2026;29(4). doi:10.1007/s10044-026-01809-6
BibTeX
@article{Nakamura2026,
author = {Nakamura, Kensuke and Sohn, Bong-Soo and Korman, Simon and Hong, Byung-Woo},
title = {Revisiting the training of generative adversarial networks via non-leaking rotational data augmentation},
journal = {Pattern Analysis and Applications},
year = {2026},
volume = {29},
number = {4},
doi = {10.1007/s10044-026-01809-6}
}
EUVIMED