Research map / Detection and segmentation / CNN features
Representative Forgery Mining for Fake Face Detection
Chengrui Wang, Weihong Deng
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 RFM to Xception | Xception · DFFD | TDR at FDR 0.01%: 77.92 -> 90.44 | Improved |
| Add RFM to Xception | Xception · Celeb-DF | TDR at FDR 0.1%: 89.11 -> 93.88 | Improved |
| Add RFM to Patch | Patch · DFFD Group A | TDR at FDR 0.01%: 99.23 -> 99.68 | Improved |
| Add RFM to Patch | Patch · DFFD Group B | TDR at FDR 0.1%: 99.58 -> 99.56 | No clear effect |
| Replace baseline training with RFM training | Xception · DFFD Group B | TDR at FDR 0.01%: 83.46 -> 93.80 | Improved |
| Use FAM-guided multiple erasing blocks rather than the baseline | Xception · DFFD | TDR at FDR 0.01%: +8.33% | Improved |
| Add multiple erasing blocks with random anchors (ablation) | RFM · DFFD | TDR at FDR 0.01%: +0.51% | Improved |
| Add FAM guidance for selecting sensitive regions (ablation) | RFM · DFFD | TDR at FDR 0.01%: +2.21% | Improved |
| Replace SFE with progressive erasing (PSFE) (ablation) | RFM · DFFD | TDR at FDR 0.01%: 92.84 vs 92.78; 95.34 vs 95.50 | No clear effect |
| Increase erase size from 30 to 120 at p 0.5 (ablation) | RFM · Celeb-DF-subsetA | AUC: 97.89 -> 96.79 | Hurt |
| Increase erase probability from 0.5 to 1.0 at size 30 (ablation) | RFM · Celeb-DF-subsetA | AUC: 97.89 -> 97.32 | Hurt |
| Use Adversarial Erasing instead of RFM (ablation) | Xception · Celeb-DF | TDR at FDR 0.01%: 84.22 -> 76.63 | Hurt |
Closest papers by meaning
- An Information Theoretic Approach for Attention-Driven Face Forgery Detection (ECCV 2022 · similarity 0.90)
- Generalizing Face Forgery Detection With High-Frequency Features (CVPR 2021 · similarity 0.90)
- On the Detection of Digital Face Manipulation (CVPR 2020 · similarity 0.89)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.87)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.87)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · 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.
