Research map / Detection and segmentation / Open-set and few-shot detection
Real Appearance Modeling for More General Deepfake Detection
Jiahe Tian, Cai Yu, Xi Wang, Peng Chen, Zihao Xiao, Jiao Dai, Yesheng Chai, Jizhong Han
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 |
|---|---|---|---|
| add Real Appearance Modeling recovery task (ablation) | ViT-B baseline · Celeb-DF v2 / DFDC / DFDCp | AUC (%): 92.5 -> 94.2 (CDF); 75.5 -> 77.4 (DFDC); 85.9 -> 88.6 (DFDCp) | Improved |
| add Structure Disturbance pseudo-fakes (ablation) | Baseline + RAM · DFDC | AUC (%): 77.4 -> 79.1 | Improved |
| add Structure Disturbance pseudo-fakes (ablation) | Baseline + RAM · DFDCp | AUC (%): 88.6 -> 88.4 | No clear effect |
| add Multi-layer Token Fusion block (ablation) | RAE · Celeb-DF v2 / DFDC / DFDCp | AUC (%): 94.7 -> 95.5 (CDF); 79.1 -> 80.2 (DFDC); 88.4 -> 89.5 (DFDCp) | Improved |
| train on disturbed pseudo-fakes with recovery instead of detectors trained on real fake faces | RAE vs TALL/IDDDM · Celeb-DF v2 | AUC (%): 90.8 -> 95.5 | Improved |
| RAE on false positives for real faces vs SBI | ENB4+SBI · VoxCeleb / FFHQ | frame-level FP rate (%): 59.2 -> 6.9 (VoxCeleb); 57.7 -> 36.9 (FFHQ) | Improved |
| RAE on diffusion deepfakes | ENB4+SBI · DeepFakeFace average | AUC (%): 68.6 -> 70.8 | Improved |
| RAE on DFD vs PCL+I2G | RAE · DFD | AUC (%): 99.0 vs 99.0 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- UIA-ViT — UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection (ECCV 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes (NeurIPS 2025 · similarity 0.89)
- DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion (NeurIPS 2024 · similarity 0.88)
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · similarity 0.88)
- Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection (AAAI 2025 · similarity 0.87)
- Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes (NeurIPS 2025 · similarity 0.87)
- FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge (NeurIPS 2024 · 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.
