SAFIRE: Segment Any Forged Image Region
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (4) · 4437-4445
DOI: 10.1609/aaai.v39i4.32467 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Myung-Joon Kwon und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref).
Abstract (Originalsprache)
Most techniques approach the problem of image forgery localization as a binary segmentation task, training neural networks to label original areas as 0 and forged areas as 1. In contrast, we tackle this issue from a more fundamental perspective by partitioning images according to their originating sources. To this end, we propose Segment Any Forged Image Region (SAFIRE), which solves forgery localization using point prompting. Each point on an image is used to segment the source region containing itself. This allows us to partition images into multiple source regions, a capability achieved for the first time. Additionally, rather than memorizing certain forgery traces, SAFIRE naturally focuses on uniform characteristics within each source region. This approach leads to more stable and effective learning, achieving superior performance in both the new task and the traditional binary forgery localization.
Zitieren
APA
Kwon, M., Lee, W., Nam, S., Son, M., & Kim, C. (2025). SAFIRE: Segment Any Forged Image Region. Proceedings of the AAAI Conference on Artificial Intelligence, 39(4), 4437-4445. https://doi.org/10.1609/aaai.v39i4.32467
Vancouver
Kwon M, Lee W, Nam S, Son M, Kim C. SAFIRE: Segment Any Forged Image Region. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(4):4437-4445. doi:10.1609/aaai.v39i4.32467
BibTeX
@article{Kwon2025,
author = {Kwon, Myung-Joon and Lee, Wonjun and Nam, Seung-Hun and Son, Minji and Kim, Changick},
title = {SAFIRE: Segment Any Forged Image Region},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {4},
pages = {4437--4445},
doi = {10.1609/aaai.v39i4.32467}
}
EUVIMED