AI Paper Atlas

Research map / Image generation / GANs

RepMix: Representation Mixing for Robust Attribution of Synthesized Images

Tu Bui, Ning Yu, John Collomosse

ECCV 2022 · Image generation › GANs · approach: GAN-based image manipulation · 43 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 RepMix layer (ablation)RepMix · Attribution88 subset (2 train semantics)attribution accuracy: 0.7188 -> 0.7400Improved
add compound loss (ablation)RepMix · Attribution88 subset (2 train semantics)attribution accuracy: 0.7204 -> 0.7400Improved
add compound loss (ablation)RepMix · Attribution88 subset (2 train semantics)detection accuracy: 0.9364 -> 0.9426Improved
add ImageNet-C perturbation augmentation (ablation)RepMix · Attribution88 subset (2 train semantics)attribution accuracy: 0.2762 -> 0.7400Improved
use ResNet50 instead of AlexNet backbone (ablation)RepMix · Attribution88 subset (2 train semantics)attribution accuracy: 0.5280 -> 0.7400Improved
use ResNet50 instead of VGG16 backbone (ablation)RepMix · Attribution88 subset (2 train semantics)attribution accuracy: 0.7150 -> 0.7400Improved
use RepMix instead of Yu et al. approachRepMix · Attribution88attribution accuracy: 0.6784 -> 0.8207Improved
use RepMix instead of Yu et al. under I-FGSM attackRepMix · Attribution88accuracy at eps=32/255: 22.49% -> 46.35%Improved
mix images at pixel level (MixUp) instead of at a later feature layer (ablation)RepMix · Attribution88attribution accuracyHurt
increase number of mixed samples to 4 (ablation)RepMix · Attribution88attribution accuracy: 1% improvement at 4 mixing samples at mostNo clear effect
increase number of seen semantics from 2 to 11 (ablation)RepMix · Attribution88attribution accuracy: 59% -> 90%Improved

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