# SGS: Segmentation-Guided Scoring for Global Scene Inconsistencies

arXiv: https://arxiv.org/abs/2509.26039 · HTML: https://mlsanity.com/paper/2509.26039/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [Detecting and Grounding Multi-Modal Media Manipulation](https://mlsanity.com/paper/2304.02556/) (2023)
- [ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding](https://mlsanity.com/paper/2412.12718/) (2024)
- [Multimodal Fake News Detection](https://mlsanity.com/paper/2112.04831/) (2021)
- [Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation](https://mlsanity.com/paper/2309.09667/) (2023)
- [AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations](https://mlsanity.com/paper/2507.20579/) (2025)

## Abstract (arXiv)

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