AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization

Myung-Joon Kwon, Seung-Hun Nam, In-Jae Yu, Heung-Kyu Lee, Changick Kim

IJCV 2022 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection · 252 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 double JPEG pretraining of the DCT stream (ablation)CAT-Net · GRIP (copy-move)p-F1: 24.60 -> 76.45Improved
add double JPEG pretraining of the DCT stream (ablation)CAT-Net · GRIP (copy-move)p-AP: 43.43 -> 91.87Improved
add double JPEG pretraining of the DCT stream (ablation)CAT-Net · Carvalho (splicing)p-F1: 51.33 -> 78.79Improved
add double JPEG pretraining of the DCT stream (ablation)CAT-Net · Columbia (no initial compression)p-F1: 95.15 -> 93.97Hurt
add double JPEG pretraining of the DCT stream (ablation)CAT-Net · Columbia (no initial compression)p-AP: 98.21 -> 95.87Hurt
add double JPEG pretraining of the DCT stream (ablation)CAT-Net · CoMoFoD (copy-move)p-F1: 15.53 -> 14.01Hurt
add the DCT stream to the RGB stream (ablation)CAT-Net · GRIP (copy-move)p-F1: 9.46 -> 76.45Improved
add the RGB stream to the DCT stream (ablation)CAT-Net · Columbia (splicing)p-F1: 71.88 -> 93.97Improved
add the DCT stream to the RGB stream (ablation)CAT-Net · CoMoFoD (copy-move)p-F1: 17.48 -> 14.01Hurt
add DCT volume representation instead of raw DCT input (ablation)ResNet152 · Double JPEG detectionaccuracy: 54.08 -> 90.19Improved
add the quantization table (QT) input to the DCT stream (ablation)DCT Stream · Double JPEG detectionaccuracy: 91.71 -> 93.93Improved
use the DCT stream architecture instead of ResNet152 on DCT volumeDCT volume input · Double JPEG detectionaccuracy: 90.19 -> 91.71Improved

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