REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911724758630400 |
|---|---|
| author | Zhou, Jun Hu, Bingwen Wang, Yaxiong Zheng, Zhedong Wang, Yongzhen Zhang, Yuchen Liu, Ping |
| author_facet | Zhou, Jun Hu, Bingwen Wang, Yaxiong Zheng, Zhedong Wang, Yongzhen Zhang, Yuchen Liu, Ping |
| contents | Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically rely on memorizing isolated artifacts and struggle with imperceptible manipulation traces or domain shifts. Inspired by human comparative reasoning, we reformulate this task as a reference-grounded verification problem, where authenticity is assessed by comparing a query against retrieved authentic evidence. We propose REVEAL Reference-Enabled Verification for Evidence Analysis and Localization), a framework explicitly designed for this comparative paradigm. To support this paradigm, we construct a large-scale reference library comprising 170K authentic news image--text pairs featuring over 40K public figures. Technically, REVEAL employs a difference-aware fusion mechanism to capture fine-grained discrepancies between the query and retrieved evidence. Furthermore, we introduce a task-decoupled Mixture-of-Experts (MoE) architecture to jointly execute instance-level detection and fine-grained grounding, effectively mitigating optimization conflicts between these heterogeneous objectives. Extensive experiments demonstrate that REVEAL significantly outperforms state-of-the-art methods, and notably enables \emph{training-free domain adaptation} by simply updating the reference library, offering a robust and practical solution for detecting evolving misinformation. Code is available at https://anonymous.4open.science/r/REVEAL-Reference-A006. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_28459 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection Zhou, Jun Hu, Bingwen Wang, Yaxiong Zheng, Zhedong Wang, Yongzhen Zhang, Yuchen Liu, Ping Computer Vision and Pattern Recognition Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically rely on memorizing isolated artifacts and struggle with imperceptible manipulation traces or domain shifts. Inspired by human comparative reasoning, we reformulate this task as a reference-grounded verification problem, where authenticity is assessed by comparing a query against retrieved authentic evidence. We propose REVEAL Reference-Enabled Verification for Evidence Analysis and Localization), a framework explicitly designed for this comparative paradigm. To support this paradigm, we construct a large-scale reference library comprising 170K authentic news image--text pairs featuring over 40K public figures. Technically, REVEAL employs a difference-aware fusion mechanism to capture fine-grained discrepancies between the query and retrieved evidence. Furthermore, we introduce a task-decoupled Mixture-of-Experts (MoE) architecture to jointly execute instance-level detection and fine-grained grounding, effectively mitigating optimization conflicts between these heterogeneous objectives. Extensive experiments demonstrate that REVEAL significantly outperforms state-of-the-art methods, and notably enables \emph{training-free domain adaptation} by simply updating the reference library, offering a robust and practical solution for detecting evolving misinformation. Code is available at https://anonymous.4open.science/r/REVEAL-Reference-A006. |
| title | REVEAL: Reference-Grounded Reasoning for Multimodal Manipulation Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.28459 |