AI Paper Atlas

Research map / Detection and segmentation / CNN features

UCF: Uncovering Common Features for Generalizable Deepfake Detection

Zhiyuan Yan, Yong Zhang, Yanbo Fan, Baoyuan Wu

ICCV 2023 · Detection and segmentation › CNN features · approach: Forgery detection · 309 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 disentanglement framework (content removal) to Xception (ablation)Xception · CelebDF (train FF++)AUC: 0.672 -> 0.785Improved
add multi-task learning (method-specific classification) to disentanglement (ablation)UCF · CelebDF (train FF++)AUC: 0.785 -> 0.804Improved
add contrastive regularization loss (ablation)UCF · CelebDF (train FF++)AUC: 0.804 -> 0.824Improved
use AdaIN conditional decoder instead of linear addition (ablation)UCF · DFDC (train FF++)AUC: 0.786 -> 0.805Improved
detect with common features only instead of whole forgery features (ablation)UCF · CelebDF (train FF++)AUC: 0.785 -> 0.824Improved
detect with method-specific features only (ablation)UCF · CelebDF (train FF++)AUC: 0.824 -> 0.681Hurt
apply framework to ConvNeXt backbone instead of Xception (ablation)UCF · cross-dataset average (train FF++)AUC: 0.808 -> 0.866Improved
disentanglement and multi-task components on within-dataset FF++ test (ablation)UCF · FF++ (within-dataset)AUC: 0.986 -> 0.996No clear effect

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