AI Paper Atlas

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

Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy

Qing Yu, Kiyoharu Aizawa

ICCV 2019 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 148 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
use unlabeled-data discrepancy training instead of ODINtwo-head discrepancy OOD detector · CIFAR-100 ID, TINr OOD (DenseNet-BC)Detection error (%): 17.2 -> 2.0Improved
use unlabeled-data discrepancy training instead of ELOC ensembletwo-head discrepancy OOD detector · CIFAR-100 ID, TINr OOD (WRN-28-10)Detection error (%): 9.1 -> 2.3Improved
shrink unlabeled set from 9k ID + 9k OOD to 1k ID + 1k OOD (ablation)two-head discrepancy OOD detector · CIFAR-100 ID, TINc OODDetection error (%): 0.7 -> 1.5Hurt
reduce unlabeled OOD samples from 2k to 500 with 9k ID (ablation)two-head discrepancy OOD detector · CIFAR-100 ID, TINc OODDetection error (%): 0.3 -> 3.8Hurt
train unlabeled OOD on TINc, test on different LSUNc (ablation)two-head discrepancy OOD detector · CIFAR-100 IDDetection error (%): 0.2 -> 0.5Hurt
train unlabeled OOD on LSUNc, test on TINc (ablation)two-head discrepancy OOD detector · CIFAR-100 IDDetection error (%): 0.2 -> 0.7Hurt
use fine-tuning for discrepancy loss (limitation)two-head discrepancy OOD detector · classification of ID dataaccuracy drop: 5% dropHurt

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