AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

FIND: A Simple Yet Effective Baseline for Diffusion-Generated Image Detection

Jie Li, Yingying Feng, Chi Xie, Jie Hu, Lei Tan, Jiayi Ji

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Reconstruction-based diffusion image detection · 1 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 Gaussian noise to real images labeled synthetic (ablation)FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 80.58 -> 88.35Improved
add pure Gaussian noise images labeled synthetic (without noisy real images) (ablation)FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 80.58 -> 75.97Hurt
add pure Gaussian noise images on top of noisy real images (ablation)FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 88.35 -> 85.72Hurt
add noisy synthetic images labeled synthetic alone (ablation)FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 80.58 -> 74.97Hurt
add noisy synthetic images on top of noisy real images (ablation)FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 88.35 -> 84.50Hurt
switch backbone from ResNet50 to ViT-B/16FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 80.13 -> 88.35Improved
replace reconstruction (LaRE2) with noise-augmented training, RN50FIND ViT-B/16 · GenImage (average of 8 generators)accuracy: 79.07 -> 80.13Improved
remove reconstruction step versus DIREFIND ViT-B/16 · Inference speedinference time: 151.9 ms -> 0.4 msImproved
remove reconstruction step versus LaRE2FIND ViT-B/16 · Inference speedinference time: 50.4 ms -> 0.4 msImproved
increase noise magnitude epsilon beyond 20 (ablation)FIND ViT-B/16 · GenImage SD V1.5 training subsetaccuracyNo 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