AI Paper Atlas

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

Deep Hybrid Models for Out-of-Distribution Detection

Senqi Cao, Zhongfei Zhang

CVPR 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 16 citations (OpenAlex)

Check 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
Use the full DHM rather than a vanilla DNNWide ResNet-28-10 · CIFAR-10 ID / CIFAR-100 OoDAUROC: 0.868 ± 0.01 -> 1.000 ± 0.00Improved
Use the full DHM rather than a vanilla DNNWide ResNet-28-10 · CIFAR-100 ID / CIFAR-10 OoDAUROC: 0.806 ± 0.01 -> 1.000 ± 0.00Improved
Use the full DHM rather than a vanilla DNNXLNet · CLINC150 out-of-scopeAUROC: 0.975 ± 0.02 -> 1.000 ± 0.00Improved
Add a normalizing flow to the spectrally normalized classifier (ablation)DNN+SN · CIFAR-10 ID / CIFAR-100 OoDAUROC: 0.872 ± 0.01 -> 1.000 ± 0.00Improved
Add a normalizing flow to the spectrally normalized classifier (ablation)DNN+SN · CIFAR-100 ID / CIFAR-10 OoDAUROC: 0.811 ± 0.02 -> 1.000 ± 0.00Improved
Add a normalizing flow to the spectrally normalized classifier (ablation)DNN+SN · CLINC150 out-of-scopeAUROC: 0.976 ± 0.01 -> 1.000 ± 0.00Improved
Add spectral normalization to the classifier with a normalizing flow (ablation)DNN+NF · CIFAR-10 ID / CIFAR-100 OoDAUROC: 0.951 ± 0.03 -> 1.000 ± 0.00Improved
Add spectral normalization to the classifier with a normalizing flow (ablation)DNN+NF · CIFAR-100 ID / CIFAR-10 OoDAUROC: 0.945 ± 0.04 -> 1.000 ± 0.00Improved
Add spectral normalization to the classifier with a normalizing flow (ablation)DNN+NF · CLINC150 out-of-scopeAUROC: 0.991 ± 0.01 -> 1.000 ± 0.00Improved
Add spectral normalization to a vanilla classifier (ablation)Wide ResNet-28-10 · CIFAR-10 ID / CIFAR-100 OoDAUROC: 0.868 ± 0.01 -> 0.872 ± 0.01No clear effect
Add spectral normalization to a vanilla classifier (ablation)Wide ResNet-28-10 · CIFAR-100 ID / CIFAR-10 OoDAUROC: 0.806 ± 0.01 -> 0.811 ± 0.02No clear effect
Add a normalizing flow without spectral normalization (ablation)vanilla classifier · CIFAR-10 ID / CIFAR-100 OoDAUROC: 0.868 ± 0.01 -> 0.951 ± 0.03Improved

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