AI Paper Atlas

Research map / Image generation / Editing and style transfer

Attention-GAN for Object Transfiguration in Wild Images

Xinyuan Chen, Chang Xu, Xiaokang Yang, Dacheng Tao

ECCV 2018 · Image generation › Editing and style transfer · approach: Image-to-image translation · 193 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
split generator into attention and transformation networks (vs CycleGAN)CycleGAN · MSCOCO horse to zebrabackground PSNR: 18.1875 -> 22.2629Improved
split generator into attention and transformation networks (vs CycleGAN)CycleGAN · MSCOCO horse to zebrabackground SSIM: 0.6725 -> 0.9003Improved
split generator into attention and transformation networks (vs CycleGAN)CycleGAN · MSCOCO zebra to horsebackground PSNR: 18.1021 -> 21.5360Improved
split generator into attention and transformation networks (vs CycleGAN)CycleGAN · MSCOCO zebra to horsebackground SSIM: 0.7155 -> 0.8988Improved
add segmentation supervision to attention network (ablation)Attention-GAN (unsupervised) · MSCOCO horse to zebrabackground PSNR: 22.2629 -> 24.589Improved
add segmentation supervision to attention network (ablation)Attention-GAN (unsupervised) · MSCOCO horse to zebrabackground SSIM: 0.9003 -> 0.9482Improved
add segmentation supervision to attention network (ablation)Attention-GAN (unsupervised) · MSCOCO zebra to horsebackground PSNR: 21.5360 -> 23.9330Improved
add segmentation supervision to attention network (ablation)Attention-GAN (unsupervised) · MSCOCO horse foreground maskUoI (%): 28.1% -> 37.8%Improved
add segmentation supervision to attention network (ablation)Attention-GAN (unsupervised) · MSCOCO horse foreground maskmAPr@0.5 (%): 20.3% -> 30.5%Improved
add sparse loss lambda_sparse=1 (vs 0) (ablation)Attention-GAN (unsupervised) · MSCOCO horse to zebrabackground PSNR: 19.8621 -> 22.2629Improved
increase sparse loss weight from 1 to 5 (ablation)Attention-GAN (unsupervised) · MSCOCO horse to zebrabackground PSNR: 22.2629 -> 24.2173Mixed
increase sparse loss weight from 1 to 5 (ablation)Attention-GAN (unsupervised) · MSCOCO horse to zebrabackground SSIM: 0.9003 -> 0.9367Mixed

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