AI Paper Atlas

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

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 13 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Real Appearance Modeling recovery task (ablation)ViT-B baseline · Celeb-DF v2 / DFDC / DFDCpAUC (%): 92.5 -> 94.2 (CDF); 75.5 -> 77.4 (DFDC); 85.9 -> 88.6 (DFDCp)Improved
add Structure Disturbance pseudo-fakes (ablation)Baseline + RAM · DFDCAUC (%): 77.4 -> 79.1Improved
add Structure Disturbance pseudo-fakes (ablation)Baseline + RAM · DFDCpAUC (%): 88.6 -> 88.4No clear effect
add Multi-layer Token Fusion block (ablation)RAE · Celeb-DF v2 / DFDC / DFDCpAUC (%): 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 facesRAE vs TALL/IDDDM · Celeb-DF v2AUC (%): 90.8 -> 95.5Improved
RAE on false positives for real faces vs SBIENB4+SBI · VoxCeleb / FFHQframe-level FP rate (%): 59.2 -> 6.9 (VoxCeleb); 57.7 -> 36.9 (FFHQ)Improved
RAE on diffusion deepfakesENB4+SBI · DeepFakeFace averageAUC (%): 68.6 -> 70.8Improved
RAE on DFD vs PCL+I2GRAE · DFDAUC (%): 99.0 vs 99.0No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy