AI Paper Atlas

Research map / Detection and segmentation / CNN features

DOA-GAN: Dual-Order Attentive Generative Adversarial Network for Image Copy-Move Forgery Detection and Localization

Ashraful Islam, Chengjiang Long, Arslan Basharat, Anthony Hoogs

CVPR 2020 · Detection and segmentation › CNN features · approach: Forgery detection · 178 citations (OpenAlex)

Check 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
Combine first- and second-order attention (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 94.33 -> 96.48Improved
Combine first- and second-order attention (ablation)DOA-GAN · USC-ISI CMFD test, forged imagestarget pixel F1: 65.90 -> 81.72Improved
Add adversarial loss (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 94.25 -> 96.48Improved
Add adversarial loss (ablation)DOA-GAN · USC-ISI CMFD test, forged imagestarget pixel F1: 80.45 -> 81.72Improved
Add detection loss (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 92.49 -> 96.48Improved
Add ASPP-1 (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 94.10 -> 96.48Improved
Add ASPP-2 (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 92.35 -> 96.48Improved
Add both attention orders instead of no attention (ablation)DOA-GAN · USC-ISI CMFD testdetection F1: 82.82 -> 96.48Improved
Use DOA-GAN rather than BusterNetCopy-move detection and localization · CASIA CMFDlocalization F1: 33.72 -> 41.44Improved
Use DOA-GAN rather than BusterNetCopy-move detection and localization · CoMoFoDdetection F1: 55.22 -> 63.05Improved
Use DOA-GAN rather than BusterNetCopy-move detection and localization · CoMoFoDlocalization F1: 35.34 -> 36.92Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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