Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Yuchu, Chu, Jiaming, Zhao, Jian, Zhang, Xin, Yang, Xu, Jin, Lei, Zhang, Chi, Li, Xuelong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911351542120448
author Jiang, Yuchu
Chu, Jiaming
Zhao, Jian
Zhang, Xin
Yang, Xu
Jin, Lei
Zhang, Chi
Li, Xuelong
author_facet Jiang, Yuchu
Chu, Jiaming
Zhao, Jian
Zhang, Xin
Yang, Xu
Jin, Lei
Zhang, Chi
Li, Xuelong
contents The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection
Jiang, Yuchu
Chu, Jiaming
Zhao, Jian
Zhang, Xin
Yang, Xu
Jin, Lei
Zhang, Chi
Li, Xuelong
Computer Vision and Pattern Recognition
Artificial Intelligence
The proliferation of generative models has raised serious concerns about visual content forgery. Existing deepfake detection methods primarily target either image-level classification or pixel-wise localization. While some achieve high accuracy, they often suffer from limited generalization across manipulation types or rely on complex architectures. In this paper, we propose Loupe, a lightweight yet effective framework for joint deepfake detection and localization. Loupe integrates a patch-aware classifier and a segmentation module with conditional queries, allowing simultaneous global authenticity classification and fine-grained mask prediction. To enhance robustness against distribution shifts of test set, Loupe introduces a pseudo-label-guided test-time adaptation mechanism by leveraging patch-level predictions to supervise the segmentation head. Extensive experiments on the DDL dataset demonstrate that Loupe achieves state-of-the-art performance, securing the first place in the IJCAI 2025 Deepfake Detection and Localization Challenge with an overall score of 0.846. Our results validate the effectiveness of the proposed patch-level fusion and conditional query design in improving both classification accuracy and spatial localization under diverse forgery patterns. The code is available at https://github.com/Kamichanw/Loupe.
title Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.16819