Research map / Detection and segmentation / Open-set and few-shot detection
EARG-Net: Edge-Aware Reconstruction-Guided Network for Image Manipulation Detection and Localization
Yanpu Yu, Zhaoxin Shi, Hanqing Zhao, Tianyi Wei, Wenbo Zhou, Nenghai Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use EATM edge-aware masking instead of random masking (ratio 0.50) (ablation) | EARG-Net · CASIAv1 (CAT protocol) | F1: 0.163 -> 0.498 | Improved |
| use EATM instead of random masking (ratio 0.50) (ablation) | EARG-Net · CASIAv1 (CAT protocol) | AUC: 0.575 -> 0.840 | Improved |
| use EATM instead of random masking (ratio 0.50) (ablation) | EARG-Net · NIST16 (CAT protocol) | F1: 0.131 -> 0.589 | Improved |
| use EATM instead of random masking (ratio 0.50) (ablation) | EARG-Net · NIST16 (CAT protocol) | AUC: 0.607 -> 0.881 | Improved |
| raise EATM masking ratio from 0.25 to 0.75 (ablation) | EARG-Net · CASIAv1 (CAT protocol) | F1: 0.487 -> 0.498 | No clear effect |
| add EIF stream to RGB-only model (ablation) | EARG-Net · NIST16 (Protocol-MVSS) | F1: 0.135 -> 0.269 | Improved |
| add EIF stream to RGB-only model (ablation) | EARG-Net · AutoSplice (Protocol-MVSS) | AUC: 0.363 -> 0.526 | Improved |
| add RGB stream to EIF-only model (ablation) | EARG-Net · NIST16 (Protocol-MVSS) | AUC: 0.783 -> 0.871 | Improved |
| add RGB stream to EIF-only model (ablation) | EARG-Net · AutoSplice (Protocol-MVSS) | F1: 0.184 -> 0.334 | Improved |
| add EIF stream to RGB-only model (ablation) | EARG-Net · AutoSplice (Protocol-MVSS) | F1: 0.193 -> 0.334 | Improved |
Closest papers by meaning
- Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization (NeurIPS 2026 · similarity 0.87)
- Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods (CVPR 2024 · similarity 0.86)
- Training-Free Image Manipulation Localization Using Diffusion Models (AAAI 2025 · similarity 0.86)
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.86)
- UnionFormer: Unified-Learning Transformer with Multi-View Representation for Image Manipulation Detection and Localization (CVPR 2024 · similarity 0.85)
- InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models (AAAI 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
