SAFIRE: Segment Any Forged Image Region

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kwon, Myung-Joon, Lee, Wonjun, Nam, Seung-Hun, Son, Minji, Kim, Changick
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909424596025344
author Kwon, Myung-Joon
Lee, Wonjun
Nam, Seung-Hun
Son, Minji
Kim, Changick
author_facet Kwon, Myung-Joon
Lee, Wonjun
Nam, Seung-Hun
Son, Minji
Kim, Changick
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08197
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SAFIRE: Segment Any Forged Image Region
Kwon, Myung-Joon
Lee, Wonjun
Nam, Seung-Hun
Son, Minji
Kim, Changick
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
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.
title SAFIRE: Segment Any Forged Image Region
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2412.08197