AI Paper Atlas

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

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Xin Dong, Junfeng Guo, Ang Li, Wei-Te Ting, Cong Liu, H.T. Kung

CVPR 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 43 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 channel-wise neural mean discrepancies from a pretrained ConvNet with a logistic-regression detector instead of statistical kernel baselinesConvNet (4 layers) · CIFAR-10 vs SVHNAUROC: 84.9 -> 99.9Improved
Use channel-wise neural mean discrepancies from a pretrained ConvNet with a logistic-regression detector instead of statistical kernel baselinesConvNet (4 layers) · SVHN vs CIFAR-10AUROC: 80.3 -> 99.8Improved
Use NMD-MLP instead of the strongest listed baselineResNet-34 OOD detection · CIFAR-10 ID; Texture OODAUROC: 97.5 -> 98.9Improved
Use NMD-MLP instead of the strongest listed baselineResNet-34 OOD detection · CIFAR-10 ID; CIFAR-100 OODAUROC: 87.2 -> 90.1Improved
Use NMD-MLP instead of the strongest listed baselineResNet-34 OOD detection · CIFAR-10 ID; LSUN-C OODAUROC: 98.8 -> 98.8No clear effect
Train the detector on CIFAR-100 and transfer it to unseen OOD dataNMD with ResNet-34 · CIFAR-10 ID; LSUN-C, SVHN, Texture, and ImageNet-C unseen OODAUROCImproved
Replace activation mean discrepancy with activation variance discrepancy (ablation)NMD detector · CIFAR-10 vs CIFAR-100AUROC: 95.4 -> 95.3No clear effect
Add activation variance discrepancy and concatenate it with NMD (ablation)NMD detector · CIFAR-10 vs CIFAR-100AUROC: 95.4 -> 95.6Improved
Use an untrained rather than pretrained ResNet-34 to compute NMD (ablation)NMD detector · OOD batch detectionAUROCHurt
Use only the first five layers' NMD values rather than more layers (ablation)NMD detector · CIFAR-10 vs SVHNAUROCNo clear effect
Use more NMD layers to capture semantic differences (ablation)NMD detector · CIFAR-10 vs CIFAR-100AUROCImproved
Use a higher-capacity MLP rather than LR with few training examples (ablation)NMD detector · Few-shot OOD trainingdetection performanceHurt

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