Research map / Detection and segmentation / CNN features
End-to-End Reconstruction-Classification Learning for Face Forgery Detection
Check 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 |
|---|---|---|---|
| Use RECCE instead of the strongest listed baseline | Xception face-forgery detector · FF++ c40 | AUC (%): 93.30 -> 95.02 | Helped |
| Use RECCE instead of the strongest listed baseline | Xception face-forgery detector · WildDeepfake | AUC (%): 90.71 -> 92.02 | Helped |
| Use RECCE instead of the strongest listed baseline | Xception face-forgery detector · DFDC | LogLoss: 0.4916 -> 0.4341 | Helped |
| Add reconstruction learning to the baseline (ablation) | Xception on WildDeepfake · WildDeepfake | AUC (%): 86.76 -> 89.61 | Helped |
| Add multi-scale graph reasoning (ablation) | RECCE on WildDeepfake · WildDeepfake | AUC (%): 91.10 -> 92.02 | Helped |
| Add reconstruction guided attention (ablation) | RECCE on WildDeepfake · WildDeepfake | AUC (%): 89.71 -> 92.02 | Helped |
| Add reconstruction learning, MGR, and RGA (ablation) | Xception on WildDeepfake · WildDeepfake | Acc (%): 77.25 -> 83.25 | Helped |
| Train the reconstruction network on real faces only, not real and fake faces (ablation) | RECCE on WildDeepfake · WildDeepfake | AUC (%): 88.92 -> 92.02 | Helped |
| Add the metric-learning loss (ablation) | Real-only reconstruction model on WildDeepfake · WildDeepfake | AUC (%): 90.49 -> 92.02 | Helped |
| Use RECCE instead of MultiAtt | Face-forgery detector under common image perturbations · WildDeepfake perturbation average | AUC (%): 85.95 -> 88.75 | Helped |
Closest papers by meaning
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · similarity 0.90)
- Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection (CVPR 2025 · similarity 0.88)
- Critical Forgetting-Based Multi-Scale Disentanglement for Deepfake Detection (AAAI 2025 · similarity 0.88)
- Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection (CVPR 2025 · similarity 0.88)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.87)
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces (NeurIPS 2025 · 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.