Research map / Image generation / Autoregressive and latent generation
Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification
Jiangling Zhang, Shuxuan Gao, Bofan Liu, Siqiang Feng, Jirui Huang, Yaxiong Chen, Ziyu Chen
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 |
|---|---|---|---|
| add dual-stream segmentation network (DSSN) (ablation) | single-stream baseline · GIT average | IoU: 0.670 -> 0.684 | Improved |
| add DSSN (ablation) | single-stream baseline · TT average | IoU: 0.459 -> 0.483 | Improved |
| add TAPI module on top of DSSN (ablation) | IFA-Net · GIT average | IoU: 0.684 -> 0.745 | Improved |
| add TAPI module on top of DSSN (ablation) | IFA-Net · TT average | F1: 0.625 -> 0.670 | Improved |
| add Adaptive Decoder (ablation) | IFA-Net · GIT average | F1: 0.823 -> 0.855 | Improved |
| add Adaptive Decoder (ablation) | IFA-Net · TT average | IoU: 0.554 -> 0.586 | Improved |
| full IFA-Net vs single-stream baseline (ablation) | IFA-Net · GIT average | IoU: 0.670 -> 0.778 | Improved |
| IFA-Net vs strongest baseline DcDsDiff on traditional tampering | IFA-Net · TT average | IoU: 0.625 -> 0.586 | Hurt |
| IFA-Net vs DcDsDiff on diffusion tampering | IFA-Net · GIT average | IoU: 0.713 -> 0.778 | Improved |
| IFA-Net vs DcDsDiff under strong Gaussian blur and heavy JPEG | IFA-Net · GIT/TT robustness | F1 | Mixed |
Closest papers by meaning
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.87)
- Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization (AAAI 2025 · similarity 0.87)
- A Lottery Ticket Hypothesis Approach with Sparse Fine-tuning and MAE for Image Forgery Detection and Localization (AAAI 2025 · similarity 0.87)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.86)
- DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization (CVPR 2024 · similarity 0.86)
- Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection (CVPR 2024 · similarity 0.86)
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.
