AI Paper Atlas

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

Multiple Class Novelty Detection Under Data Distribution Shift

Poojan Oza, Hien V. Nguyen, Vishal M. Patel

ECCV 2020 · Label-efficient and robust learning › OOD and anomaly detection · approach: Uncertainty and misclassification detection · 15 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
test on shifted USPS instead of MNISTALOCC · MNIST/USPS preliminaryAUROC: 0.81 -> 0.63Hurt
add gradient reversal layer domain alignmentSoftmax · Digits novelty detection (average)AUROC: 0.620 -> 0.776Improved
add gradient reversal and classification to ALOCCALOCC · Digits novelty detection (average)AUROC: 0.667 -> 0.873Improved
replace ALOCC+GRL with cross-domain generator unified trainingALOCC+GRL · Digits novelty detection (average)AUROC: 0.873 -> 0.921Improved
replace ALOCC+GRL with cross-domain generator unified trainingALOCC+GRL · Office-31 novelty detection (average)AUROC: 0.774 -> 0.877Improved
train on unlabeled target data with ALOCC instead of source-only softmaxSoftmax · Office-31 novelty detection (average)AUROC: 0.737 -> 0.758Improved
add gradient reversal layer to ALOCCALOCC · Office-31 novelty detection (average)AUROC: 0.758 -> 0.774Improved
add domain alignment to Softmax with GRLSoftmax · Office-31 novelty detection (average)AUROC: 0.737 -> 0.762Improved
replace ALOCC+GRL with proposed method on W->DALOCC+GRL · Office-31 W->DAUROC: 0.987 -> 0.938Hurt
replace ALOCC+GRL with proposed on SVHN->USPSALOCC+GRL · Digits SVHN->USPSAUROC: 0.845 -> 0.895Improved
use target-only ALOCC instead of source-only softmaxSoftmax · Digits novelty detection (average)AUROC: 0.620 -> 0.667Improved

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