AI Paper Atlas

Research map / Image generation / GANs

Generative Image Modeling Using Style and Structure Adversarial Networks

Xiaolong Wang, Abhinav Gupta

ECCV 2016 · Image generation › GANs · approach: Large-scale GAN latent analysis · 617 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 S2-GAN pretraining instead of training from scratchdetector · NYUv2 RGBD object detection (AP, 19 classes)mean AP (%): 30.9 -> 32.4Improved
use S2-GAN discriminator instead of DCGAN pretrainingdetector · NYUv2 RGBD object detection (AP, 19 classes)mean AP (%): 30.4 -> 32.4Improved
use S2-GAN instead of DCGANv2 pretrainingdetector · NYUv2 RGBD object detection (AP, 19 classes)mean AP (%): 31.1 -> 32.4Improved
use ImageNet pretrained AlexNet instead of S2-GAN pretrainingdetector · NYUv2 RGBD object detection (AP, 19 classes)mean AP (%): 32.4 -> 37.6Hurt
use S2-GAN features instead of DCGAN discriminator for scene classificationSVM on features · SUN RGB-D scene classificationaccuracy (%): +8.2%Improved
generate images with Style and Structure decomposition instead of DCGANgenerator · AMT user study (1000 pairs)preferred as more realistic (%): 71%Improved
generate images with Style and Structure decomposition instead of DCGANgenerator · Fast-RCNN detections on generated imagesaverage detections per image (0.3 threshold): 1.72 -> 2.2Improved
generate images with Style and Structure decompositiongenerator · Places-AlexNet confidence on generated imagesmax softmax probability: around 2%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