AI Paper Atlas

Research map / Image generation / GANs

Adversarial Learning with Local Coordinate Coding

Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan

ICML 2018 · Image generation › GANs · approach: GAN latent optimization and evaluation · 31 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
Replace the standard prior sampling with LCC samplingGANs · Oxford-102Inception Score: 2.66 -> 2.71Improved
Use LCC sampling with d=30 instead of the baseline priorGANs · MNISTMS-SSIM: 0.239 -> 0.224Improved
Use LCC sampling with d=30 instead of the baseline priorGANs · Oxford-102MS-SSIM: 0.151 -> 0.153Mixed
Use LCC sampling with d=30 instead of the baseline priorGANs · LSUNMS-SSIM: 0.213 -> 0.203Improved
Use LCC sampling with d=30 instead of the baseline priorGANs · CelebAMS-SSIM: 0.308 -> 0.305Improved
Replace sparse coding with LCC codingGANs · Oxford-102 (d=5)Inception Score: 2.44 -> 2.57Improved
Replace sparse coding with LCC codingGANs · Oxford-102 (d=10)MS-SSIM: 0.179 -> 0.163Improved
Increase the LCC input dimension from d=30 to d=100 (ablation)LCC-GANs · Oxford-102Inception Score: 2.83 -> 2.75Mixed
Increase the LCC input dimension from d=30 to d=100 (ablation)LCC-GANs · Oxford-102MS-SSIM: 0.153 -> 0.147Improved
Use a smaller input dimension, d=10 instead of d=100 (ablation)LCC-GANs · Oxford-102Inception Score: 2.75 -> 2.71Mixed
Use LCC coding rather than sampling directly from a standard GaussianProgressive GANs · CelebAvisual image qualityImproved
Use LCC sampling rather than standard prior sampling at low dimensionGANs · MNIST (d=3)visual diversityImproved

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