AI Paper Atlas

Research map / Detection and segmentation / CNN features

UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection

Wanyi Zhuang, Qi Chu, Zhentao Tan, Qiankun Liu, Haojie Yuan, Changtao Miao, Zixiang Luo, Nenghai Yu

ECCV 2022 · Detection and segmentation › CNN features · approach: Forgery detection · 163 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 UPCL (unsupervised patch consistency learning) (ablation)ViT-Base · Celeb-DF-v1AUC (%): 75.32 -> 82.96Improved
add UPCL (ablation)ViT-Base · Celeb-DF-v2AUC (%): 76.25 -> 80.86Improved
replace fixed-GFR PCL supervision with UPCL (MVG-refined pseudo labels) (ablation)UIA-ViT · Celeb-DF-v1AUC (%): 77.88 -> 82.96Improved
use soft learnable consistency factors instead of fixed ones (UPCL-hard) (ablation)UIA-ViT · Celeb-DF-v1AUC (%): 78.54 -> 82.96Improved
use soft learnable consistency factors instead of fixed ones (UPCL-hard) (ablation)UIA-ViT · Celeb-DF-v2AUC (%): 78.55 -> 80.86Improved
add CWA on top of UPCL (ablation)UIA-ViT · Celeb-DF-v1AUC (%): 82.96 -> 84.77Improved
make assemble progressive (PCWA instead of CWA) (ablation)UIA-ViT · Celeb-DF-v1AUC (%): 84.77 -> 86.59Improved
make assemble progressive (PCWA instead of CWA) (ablation)UIA-ViT · Celeb-DF-v2AUC (%): 81.77 -> 82.41Improved
add UPCL and PCWA to ViT-Base (ablation)ViT-Base · Celeb-DF-v1AUC (%): 75.32 -> 86.59Improved
use patch embeddings of layer 6 rather than layers 5, 7, 8 for MVG estimation (ablation)UIA-ViT · unseen datasetsAUC (%)Improved
use standard central GFR rather than GFR low/large/small (ablation)UIA-ViT · unseen datasetsAUC (%)Improved
compare UIA-ViT with prior methods on DFDC-PUIA-ViT vs DCL · DFDC-PAUC (%): 75.80 vs 76.71Hurt

Later papers that compared with this method

1 later accepted paper reports UIA-ViT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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