AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Suppressing Gradient Conflict for Generalizable Deepfake Detection

Ming-Hui Liu, Harry Hui Cheng, Xin Luo, X.G Xu

TPAMI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 2 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 UVS module (ablation)EfficientNet backbone · Celeb-DFAUC (%): 64.59 -> 94.45Improved
add CGR module (ablation)EfficientNet backbone · Celeb-DFAUC (%): 64.59 -> 94.92Improved
add CGR on top of UVS (ablation)CS-DFD · Celeb-DFAUC (%): 94.45 -> 95.32Improved
add CGR on top of UVS (ablation)CS-DFD · DFDCAUC (%): 73.65 -> 74.97Improved
add CGR on top of UVS (ablation)CS-DFD · FF++ (test)AUC (%): 97.98 -> 98.88Improved
add online synthesized forgeries to original-only trainingXception · FF++ (test)AUC (%): 96.37 -> 94.86Hurt
add online synthesized forgeries to original-only trainingXception · Celeb-DFAUC (%): 56.75 -> 87.77Improved
add original forgeries to synthesized-only training (1+1<2)Xception · Celeb-DFAUC (%): 90.11 -> 87.77Hurt
train on synthesized forgeries instead of originalViT-L · FF++ (test)AUC (%): 97.65 -> 70.32Hurt
apply CS-DFD instead of naive O+S trainingXception · FF++ (test)AUC (%): 94.86 -> 97.48Improved
apply CS-DFD instead of naive O+S trainingViT-L · Celeb-DFAUC (%): 85.15 -> 90.26Improved
apply CS-DFD instead of naive O+S trainingViT-B · Celeb-DFAUC (%): 91.28 -> 93.66Improved

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