AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Improving GANs for Long-Tailed Data through Group Spectral Regularization

Harsh Rangwani, Naman Jaswani, Tejan Karmali, Varun Jampani, R. Venkatesh Babu

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 26 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 gSRSNGAN · CIFAR-10-LT (imbalance 100)FID: 30.62 -> 18.58Improved
add gSRBigGAN · CIFAR-10-LT (imbalance 100)FID: 19.55 -> 12.03Improved
add gSRBigGAN · LSUN-LT (imbalance 1000)FID: 45.89 -> 24.93Improved
add gSRSNGAN · CIFAR-10-LT (imbalance 1000)IS: 6.19 -> 5.92Hurt
add gSR at 128x128BigGAN · LSUN-LT 128x128 (imbalance 100)FID: 61.63 -> 16.56Improved
add gSRStyleGAN2-ADA · CIFAR-10-LT (imbalance 100)FID: 71.09 -> 22.76Improved
add gSRBigGAN · iNaturalist 2019FID: 6.87 -> -0.51 FID (7.42%)Improved
add gSR alone without LeCam+DiffAug (ablation)SNGAN · CIFAR-10-LT (imbalance 100)FID: 31.73 -> 27.85Improved
add LeCam+DiffAug alone without gSR (ablation)SNGAN · CIFAR-10-LT (imbalance 100)FID: 31.73 -> 30.62No clear effect
add gSR on top of LeCam+DiffAug (ablation)SNGAN · CIFAR-10-LT (imbalance 100)FID: 30.62 -> 18.58Improved
use gSR instead of group spectral normalization (ablation)SNGAN · CIFAR-10-LT (imbalance 100)FID: 23.97 -> 18.58Improved
use gSR instead of gSRIP (ablation)SNGAN · CIFAR-10-LT (imbalance 100)FID: 23.67 -> 18.58Improved

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