AI Paper Atlas

Research map / Image generation / GANs

CVAE-GAN: Fine-Grained Image Generation Through Asymmetric Training

Jianmin Bao, Dong Chen, Fang Wen, Houqiang Li, Gang Hua

ICCV 2017 · Image generation › GANs · approach: GAN-based image manipulation · 624 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 mean feature matching to conditional GAN (FM-CGAN vs CGAN)CGAN · FaceScrub generated facestop-1 accuracy of generated samples: 61.97% -> 79.76%Improved
add encoder with pair-wise feature matching and pixel loss (CVAE-GAN vs FM-CGAN)FM-CGAN · FaceScrub generated facestop-1 accuracy of generated samples: 79.76% -> 97.78%Improved
add mean feature matching to CGANCGAN · FaceScrub generated facesrealism (Inception Score): 15.79 -> 19.40Improved
add encoder pair-wise matching to FM-CGANFM-CGAN · FaceScrub generated facesrealism (Inception Score): 19.40 -> 19.03No clear effect
use CVAE-GAN instead of CVAECVAE · FaceScrub generated facestop-1 accuracy of generated samples: 8.09% -> 97.78%Improved
add adversarial feature loss L_G(D) (ablation)CVAE-GAN · FaceScrub, CUB-200, Flower (qualitative)image sharpnessImproved
add pixel-level reconstruction loss L_G(img) (ablation)CVAE-GAN · FaceScrub, CUB-200, Flower (qualitative)image detailImproved
add classification feature loss L_G(C) (ablation)CVAE-GAN · FaceScrub, CUB-200, Flower (qualitative)category informationImproved
augment training with generated images of existing identitiesface recognition model · LFWverification accuracy: 91.87% -> 92.77%Improved
augment training with generated images of 5k new mixed identitiesface recognition model · LFWverification accuracy: 91.87% -> 92.98%Improved

Later papers that compared with this method

3 later accepted papers report CVAE-GAN as a baseline in their results tables; 3 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