English

SGS: Segmentation-Guided Scoring for Global Scene Inconsistencies

Computer Vision and Pattern Recognition 2025-10-01 v1

Abstract

We extend HAMMER, a state-of-the-art model for multimodal manipulation detection, to handle global scene inconsistencies such as foreground-background (FG-BG) mismatch. While HAMMER achieves strong performance on the DGM4 dataset, it consistently fails when the main subject is contextually misplaced into an implausible background. We diagnose this limitation as a combination of label-space bias, local attention focus, and spurious text-foreground alignment. To remedy this without retraining, we propose a lightweight segmentation-guided scoring (SGS) pipeline. SGS uses person/face segmentation masks to separate foreground and background regions, extracts embeddings with a joint vision-language model, and computes region-aware coherence scores. These scores are fused with HAMMER's original prediction to improve binary detection, grounding, and token-level explanations. SGS is inference-only, incurs negligible computational overhead, and significantly enhances robustness to global manipulations. This work demonstrates the importance of region-aware reasoning in multimodal disinformation detection. We release scripts for segmentation and scoring at https://github.com/Gaganx0/HAMMER-sgs

Keywords

Cite

@article{arxiv.2509.26039,
  title  = {SGS: Segmentation-Guided Scoring for Global Scene Inconsistencies},
  author = {Gagandeep Singh and Samudi Amarsinghe and Urawee Thani and Ki Fung Wong and Priyanka Singh and Xue Li},
  journal= {arXiv preprint arXiv:2509.26039},
  year   = {2025}
}

Comments

6 pages, 3 figures

R2 v1 2026-07-01T06:07:16.468Z