AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning

Zhi Chen, Jiang Duan, Kang Li, Guoping Qiu

TPAMI 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Deep one-class and tabular anomaly detection · 65 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 multiple discriminators (ensemble of up to 21) instead of one (ablation)EAL-GAN · 20 real-world datasetsAUC and GmeanImproved
add ensemble learning loss with modulating factors instead of standard adversarial loss (ablation)EAL-GAN · synthetic datasetsAUC and GmeanImproved
add embedding layer (projection discriminator) to discriminator (ablation)EAL-GAN · synthetic datasetsAUC and GmeanImproved
add ensemble active sampling instead of random sampling (ablation)EAL-GAN · synthetic datasetsAUC and GmeanImproved
use one ensemble of discriminators instead of a single discriminator (ablation)EAL-GAN · synthetic single-cluster dataAUC and GmeanImproved
train detector on real plus generated data instead of generated data only (ablation)EAL-GAN · 20 real-world datasetsAUC: 0.906 -> 0.938Improved
train detector on generated data only versus real data only (ablation)EAL-GAN · 20 real-world datasetsAUC: 0.911 vs 0.906No clear effect
increase Fake:Real ratio beyond 100:1 (ablation)EAL-GAN · 20 real-world datasetsAUC: 0.958 -> 0.955Hurt
increase labeled sampling ratio from 5% to 95% (ablation)EAL-GAN · 20 real-world datasetsAUC: 0.951 -> 0.977Improved
use 4-layer generator instead of 3-layer or 5-layer (ablation)EAL-GAN · 20 real-world datasetsAUC: 0.9% over 3-layer, 0.5% over 5-layerImproved
use EAL-GAN instead of unsupervised baselines on large datasetsEAL-GAN vs CBLOF · large datasets (12)AUC gain (%): +10.24 -> +20.66Improved
compare EAL-GAN to best deep baseline DevNetEAL-GAN · 20 real-world datasetsaverage AUC: 0.900 -> 0.951Improved

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