Loupe: A Generalizable and Adaptive Framework for Image Forgery Detection
This addresses the need for generalizable and adaptive deepfake detection tools for security and media verification, though it appears incremental as it builds on existing classification and localization methods.
The paper tackles the problem of detecting and localizing image forgeries by proposing Loupe, a lightweight framework that integrates patch-aware classification and segmentation with conditional queries, achieving state-of-the-art performance with an overall score of 0.846 on the DDL dataset and winning the IJCAI 2025 challenge.
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.