AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

The Value of AI Guidance in Human Examination of Synthetically-Generated Faces

Aidan Boyd, Patrick Tinsley, Kevin Bowyer, Adam Czajka

AAAI 2023 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 17 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
Show humans the AI's classification decisionHuman examination of synthetic faces · Synthetic face imageshuman accuracy: 56% -> 59%Improved
Show the human-guided AI's decision rather than the traditional model's decisionHuman examination of synthetic faces · Synthetic face imageshuman accuracy: 59% -> 61%Improved
Show CAM saliency without the AI decisionHuman examination of synthetic faces · Synthetic face imageshuman accuracy: 56%No clear effect
Add CAM saliency to the AI decisionHuman examination of synthetic faces · Synthetic face imageshuman accuracy: 59% -> 56%Hurt
Train the detector with human salience guidanceHuman-AI synthetic face examination · Synthetic face imageshuman accuracy: 59% -> 61%Improved
Train the detector with human salience guidanceSynthetic face examination using CAM · Synthetic face images, CAM OnlyMSE between human annotations and model saliency: 0.24 -> 0.13Improved
Give no AI assistanceHuman examination of synthetic faces · Synthetic face imagesaccuracy: 51.88%±15.51%No clear effect
Use a 90%-accurate AI decision instead of the traditional 50%-accurate AI decisionHuman examination of synthetic faces · Synthetic face images, AI accuracy unreportedhuman accuracy: 57.54±16.6 -> 63.23±11.41Improved
Use a 10%-accurate AI decision instead of the traditional 50%-accurate AI decisionHuman examination of synthetic faces · Synthetic face images, AI accuracy unreportedhuman-AI agreement: 57.3±15.54 -> 47.61±11.2Hurt
Tell users a 90%-accurate AI is 90% accurate rather than provide no accuracy informationHuman examination of synthetic faces · Synthetic face images, actual AI accuracy 90%human accuracy: 63.23±11.41 -> 65.15±11.74Improved
Tell users a 60%-accurate AI is 90% accurate rather than 60% accurateHuman examination of synthetic faces · Synthetic face images, actual AI accuracy 60%human-AI agreement: 55.69±12.92 -> 59.59±16.71Improved
Tell users a 90%-accurate AI is 60% accurate rather than 90% accurateHuman examination of synthetic faces · Synthetic face images, actual AI accuracy 90%human-AI agreement: 65.38±12.04 -> 62.37±10.63Hurt

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