Towards Generalizable Forgery Detection and Reasoning
Paper
•
2503.21210
•
Published
Model type: FakeReasoning is a forgery detection and reasoning framework with three key components: 1) a dual-branch visual encoder that integrates CLIP and DINO to capture both high-level semantics and low-level artifacts; 2) a Forgery-Aware Feature Fusion Module that leverages DINO's attention maps and cross-attention mechanisms to guide MLLMs toward forgery-related clues; 3) a Classification Probability Mapper that couples language modeling and forgery detection, enhancing overall performance.
Project page: https://pris-cv.github.io/FakeReasoning/
Paper: https://arxiv.org/abs/2503.21210
FakeReasoning is licensed under the Apache 2.0 License.