Research map / Detection and segmentation / CNN features
Generalizing Face Forgery Detection With High-Frequency Features
Yuchen Luo, Yong Zhang, Junchi Yan, Wei Liu
Check 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 the two-stream RGB and high-frequency model instead of RGB-only detection (ablation) | Xception face forgery detector · FF++ F2F training → FS | AUC: 0.762 -> 0.922 | Improved |
| Replace RGB input with SRM noise residuals (ablation) | Xception face forgery detector · FF++ F2F training → NT | AUC: 0.696 -> 0.858 | Improved |
| Add residual-guided spatial attention (ablation) | Two-stream Fusion · FF++ F2F training → FS | AUC: 0.922 -> 0.966 | Improved |
| Add dual cross-modality attention (ablation) | Fusion + RSA · FF++ F2F training → FS | AUC: 0.966 -> 0.975 | Improved |
| Add multi-scale high-frequency feature extraction (ablation) | Fusion + RSA + DCMA · FF++ F2F training → FS | AUC: 0.975 -> 0.987 | Improved |
| Use the proposed model instead of Face X-ray | Face forgery detection · FF++ HQ → DFD | AUC: 0.856 -> 0.919 | Improved |
| Use the proposed model instead of Face X-ray | Face forgery detection · FF++ HQ → DFDC | AUC: 0.700 -> 0.797 | Improved |
| Use the proposed model instead of Face X-ray | Face forgery detection · FF++ HQ → CelebDF | AUC: 0.742 -> 0.794 | Improved |
| Use the proposed model instead of Face X-ray | Face forgery detection · FF++ HQ → DF1.0 | AUC: 0.723 -> 0.738 | Improved |
| Use the proposed model instead of F3Net | Video forgery detection · FF++ LQ, FS | accuracy: 0.965 -> 0.929 | Hurt |
| Use the proposed model instead of F3Net | Video forgery detection · FF++ LQ, DF | accuracy: 0.980 -> 0.986 | Improved |
| Use the proposed model instead of ForensicTrans | F2F-trained face forgery detector · F2F(HQ) → FS(HQ) | accuracy: 0.726 -> 0.867 | Improved |
Closest papers by meaning
- Local Relation Learning for Face Forgery Detection (AAAI 2021 · similarity 0.90)
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues (ECCV 2020 · similarity 0.90)
- Frequency-Aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection (CVPR 2021 · similarity 0.90)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.88)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.87)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.87)
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.
