Research map / Detection and segmentation / CNN features
Local Relation Learning for Face Forgery Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 frequency input to the RGB baseline (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | ACC: 89.15% -> 89.99% | Helped |
| Add frequency input to the RGB baseline (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | AUC: 93.03% -> 93.13% | Helped |
| Add RFAM to fuse RGB and frequency features (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | ACC: 89.99% -> 90.05% | Helped |
| Add RFAM to fuse RGB and frequency features (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | AUC: 93.13% -> 93.78% | Helped |
| Add MPSM local relation learning to RGB features (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | ACC: 89.15% -> 91.06% | Helped |
| Add MPSM local relation learning to RGB features (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | AUC: 93.03% -> 94.96% | Helped |
| Combine frequency input, RFAM, and MPSM (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | ACC: 91.06% -> 91.47% | Helped |
| Combine frequency input, RFAM, and MPSM (ablation) | Local Relation Learning for Face Forgery Detection · FaceForensics++ LQ | AUC: 94.96% -> 95.21% | Helped |
| Use local relation learning instead of the Xception baseline | Face forgery detection trained on FF++ · Celeb-DF | AUC: 36.19 -> 78.26 | Helped |
| Use local relation learning instead of the Xception baseline | Face forgery detection trained on FF++ · DFDC | AUC: 48.98 -> 76.53 | Helped |
| Use local relation learning instead of the Xception baseline | Face forgery detection trained on FF++ · DFD | AUC: 87.86 -> 89.24 | Helped |
| Use MPSM with local RGB and frequency features rather than global classification | FaceForensics++ LQ NeuralTextures detection · FaceForensics++ LQ NeuralTextures | ACC: 83.32% -> 89.31% | Helped |
Closest papers by meaning
- Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection (CVPR 2025 · similarity 0.87)
- Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection (CVPR 2025 · similarity 0.87)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.87)
- 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)
- Face Forgery Video Detection via Temporal Forgery Cue Unraveling (CVPR 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.