AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

ADCD-Net: Robust Document Image Forgery Localization via Adaptive DCT Feature and Hierarchical Content Disentanglement

Kahim Wong, Jicheng Zhou, Haiwei Wu, Yain-Whar Si, Jiantao Zhou

ICCV 2025 · Image generation › Autoregressive and latent generation · approach: Robust diffusion watermarking · 7 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 DCT feature fused with RGB feature (ablation)backbone · ablation subsetavg F1: .602 -> .661Improved
add focal (within-image contrastive) loss (ablation)backbone + DCT · ablation subsetavg F1: .661 -> .682Improved
add adaptive DCT modulation by predicted alignment score (ablation)backbone + DCT + focal · ablation subsetavg F1: .682 -> .719Improved
reconstruct DCT coefficients as well as the image in HCD (ablation)ADCD-Net with HCD · ablation subsetavg F1: .715 -> .741Improved
add PPE on top of HCD (ablation)ADCD-Net with HCD · ablation subsetavg F1: .741 -> .750Improved
add HCD to PPE model (ablation)ADCD-Net with PPE · ablation subsetavg F1: .709 -> .750Improved
predicted DCT modulation score instead of fixed 1 (ablation)ADCD-Net · Blur-7F1: .572 -> .707Improved
predicted DCT modulation score instead of fixed 0 (ablation)ADCD-Net · JPEG-85F1: .717 -> .783Improved
fully using DCT features (score 1) versus disabling them (0) (ablation)ADCD-Net · Noise-30F1: -.017Hurt
fully using DCT features (score 1) versus disabling them (0) (ablation)ADCD-Net · Down-0.7 and JPEG-85F1: +.065, +.047Improved
add HCD (ablation)ADCD-Net · text-BG bias statisticDelta S_C: 0.937 -> 1.105Improved
add DCT traces (DTD vs TruFor)TruFor · text-BG bias statisticDelta S_C: 0.360 -> 0.773Improved

Later papers that compared with this method

1 later accepted paper reports ADCD-Net 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