AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Penny-Wise and Pound-Foolish in AI-Generated Image Detection

Yabin Wang, Zhiwu Huang, Zhou Su, Adam Prügel‐Bennett, Xiaopeng Hong

TPAMI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection

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 the class-aware binary term (lambda2=1) to the semantic-preserving term (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 72.46 -> 80.83Improved
add the semantic-preserving term (lambda1=1) to the class-aware binary term (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 76.20 -> 80.83Improved
add both loss terms vs neither (lambda 0,0 -> 1,1) (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 71.15 -> 80.83Improved
use lambda 1,1 instead of 0.5,0.5 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 76.73 -> 80.83Improved
increase lambdas to 2,2 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 80.83 -> 76.09Hurt
use ViT-L/14 instead of ViT-B/16 backbone (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 75.42 -> 80.83Improved
use OpenAI instead of OpenCLIP ViT-L/14 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 79.69 -> 80.83No clear effect
increase prompt length from 1 to 16 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 68.38 -> 80.83Improved
increase prompt depth from 1 to 8 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 78.30 -> 80.83Improved
train with 20 classes instead of 2 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 71.56 -> 80.83Improved
train with 20 classes instead of 16 (ablation)PoundNet · ForenSynths/DIF/Ojha averageACC: 76.71 -> 80.83Improved

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