AI Paper Atlas

Research map / Image generation / GANs

Improving Generative Adversarial Networks With Local Coordinate Coding

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

TPAMI 2020 · Image generation › GANs · approach: GAN latent optimization and evaluation · 47 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 LCC sampling (q=2) to DCGAN (ablation)DCGAN · Oxford-102FID: 182.2 -> 61.9Improved
use higher-order term (q=3) instead of q=2 in LCC (ablation)LCCGAN · Oxford-102FID: 61.9 -> 57.7Improved
add LCC (q=3) to WGAN-GP (ablation)WGAN-GP · Oxford-102FID: 160.4 -> 145.9Improved
add LCC (q=3) to StackGAN-v1 (ablation)StackGAN-v1 · Oxford-102FID: 178.8 -> 168.2Improved
add LCC (q=3) to StackGAN-v2 (ablation)StackGAN-v2 · Oxford-102FID: 27.0 -> 22.2Improved
add LCC (q=3) to Progressive GAN (ablation)Progressive GAN · Oxford-102FID: 114.5 -> 109.6Improved
add LCC (q=2) to StackGAN-v2 (ablation)StackGAN-v2 · Oxford-102IS: 3.087 -> 3.088No clear effect
increase L_nu from 0.0001 to 0.001 (ablation)LCCGAN++ · Oxford-102 (d=30)FID: 57.7 -> 205.9Hurt
set L_h to 1 instead of 0.0001 (ablation)LCCGAN++ · Oxford-102 (d=30)FID: 247.9 -> 57.7Improved
increase number of bases M from 64 to 128 (ablation)LCCGAN++ · Oxford-102 (d=30)FID: 66.3 -> 57.7Improved
increase number of bases M from 128 to 256 (ablation)LCCGAN++ · Oxford-102 (d=30)FID: 57.7 -> 76.8Hurt
use LCCGAN++ with d=5 instead of d=100 DCGANLCCGAN++ vs DCGAN · Oxford-102FID: 182.2 -> 71.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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