Research map / Video / Video segmentation and tracking
Explaining Deepfake Detection by Analysing Image Matching
Shichao Dong, Jin Wang, Jiajun Liang, Haoqiang Fan, Renhe Ji
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 |
|---|---|---|---|
| train with paired source/target real images (FST-Matching) instead of unpaired real images (ablation) | ResNet-18 detector · FF++ FaceSwap (40-identity subset) | AUC: 75.41 -> 99.91 | Improved |
| train with paired source/target real images instead of unpaired real images (ablation) | ResNet-18 detector · FF++ NeuralTexture (40-identity subset) | AUC: 76.60 -> 98.73 | Improved |
| train with paired source/target real images instead of unpaired real images (ablation) | Efficient-b3 detector · FF++ FaceSwap (40-identity subset) | AUC: 87.51 -> 100 | Improved |
| paired small subset instead of whole FF++ training set (ablation) | ResNet-18 detector · FF++ FaceSwap | AUC: 100 -> 99.91 | No clear effect |
| explicitly exploit FST-Matching (proposed model) vs Xception baseline | Xception · FF++ C40 | AUC: 81.76 -> 90.44 | Improved |
| FST-Matching model vs MAT-Efficient on light compression | Efficient-b4 · FF++ C23 | AUC: 99.29 vs 98.81 | Hurt |
| FST-Matching vs Xception on cross-dataset generalization | Xception · Celeb-DF (trained on FF++) | AUC: 49.03 -> 88.44 | Improved |
| FST-Matching vs LipForensics under noise perturbation | FST-Matching · FF++ image-editing robustness (Noise) | AUC: 73.8 -> 84.8 | Improved |
| FST-Matching vs Xception on raw videos | Xception · FF++ RAW | ACC: 99.26 vs 98.71 | No clear effect |
Closest papers by meaning
- Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning (CVPR 2025 · similarity 0.88)
- Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection (AAAI 2024 · similarity 0.87)
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes (NeurIPS 2025 · similarity 0.86)
- AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection (CVPR 2024 · similarity 0.86)
- Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection (AAAI 2025 · similarity 0.85)
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · 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.
