atlas

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

Generative-Discriminative Feature Representations for Open-Set Recognition

CVPR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 204 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 self-supervision (ablation)open-set classifier · CIFAR10 animal-known splitAUC-ROC: 84.4 -> 88.8Helped
augment the input with a generative representation, without self-supervision (ablation)open-set classifier · CIFAR10 animal-known splitAUC-ROC: 84.4 -> 88.4Helped
combine generative feature augmentation and self-supervision (ablation)open-set classifier · CIFAR10 animal-known splitAUC-ROC: 84.4 -> 91.2Helped
replace Vanilla AE with Conditioned-AE (ablation)generative representation model · CIFAR10AUC-ROC: 80.8 -> 82.0Helped
use WRN28-10 instead of Vanilla CNN (ablation)classifier with Conditioned-AE · CIFAR10AUC-ROC: 82.0 -> 83.1Helped
use WGAN instead of Conditioned-AE (ablation)WRN28-10 classifier · CIFAR10AUC-ROC: 83.1 -> 83.6Helped

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