AI Paper Atlas

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

OpenGAN: Open-Set Recognition via Open Data Generation

Shu Kong, Deva Ramanan

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 236 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
build the discriminator on off-the-shelf features instead of pixels (ablation)OpenGAN-0 · Setup-I SVHNAUROC: .881 -> .988Improved
build the nearest-neighbour detector on features instead of pixels (ablation)NN · Setup-I SVHNAUROC: .534 -> .888Improved
train on features instead of pixels (ablation)OpenGAN-0 · Setup-I MNISTAUROC: .987 -> .999Improved
train on features instead of pixels (ablation)OpenGAN-0 · Setup-I CIFARAUROC: .971 -> .973No clear effect
use BiGAN discriminator instead of reconstruction error (features) (ablation)BiGAN · Setup-I SVHNAUROC: .976 -> .993Improved
use BiGAN discriminator instead of reconstruction error (pixels) (ablation)BiGAN · Setup-I SVHNAUROC: .822 -> .880Improved
train BiGAN discriminator on features instead of pixels (ablation)BiGAN · Setup-I SVHNAUROC: .880 -> .993Improved
add GAN-generated fake open data and discriminator instead of binary classifier (features) (ablation)OpenGAN · Setup-II cross-datasetAUROC: .918 -> .984Improved
add GAN-generated fake open data instead of binary classifier (pixels) (ablation)OpenGAN · Setup-II cross-datasetAUROC: .857 -> .969Improved
train OpenGAN on pixels instead of features (ablation)OpenGAN · Setup-II cross-datasetAUROC: .984 -> .969Hurt
add real open training data (OpenGAN vs OpenGAN-0, features) (ablation)OpenGAN · Setup-II cross-dataset avgAUROCNo clear effect
add GAN generator and discriminator over binary classifier (features) (ablation)OpenGAN · Setup-III CityscapesAUROC: .861 -> .885Improved

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