AI Paper Atlas

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

Detecting Semantic Anomalies

Faruk Ahmed, Aaron Courville

AAAI 2020 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 64 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 rotation prediction as an auxiliary task (ablation)CIFAR-10 hold-out-class classifier with MSP · CIFAR-10 hold-out-classaverage precision: 34.92 ± 0.41 -> 40.22 ± 0.16Improved
Add rotation prediction as an auxiliary task (ablation)CIFAR-10 hold-out-class classifier with ODIN · CIFAR-10 hold-out-classaverage precision: 36.63 ± 0.61 -> 41.56 ± 0.15Improved
Add rotation prediction as an auxiliary task (ablation)STL-10 hold-out-class classifier with MSP · STL-10 hold-out-classaverage precision: 21.07 ± 0.25 -> 24.41 ± 0.23Improved
Add rotation prediction as an auxiliary task (ablation)STL-10 hold-out-class classifier with ODIN · STL-10 hold-out-classaverage precision: 22.27 ± 0.29 -> 25.14 ± 0.45Improved
Add rotation prediction as an auxiliary task (ablation)CIFAR-10 classifier · CIFAR-10 hold-out-classaccuracy: 96.03 ± 0.00 -> 96.83 ± 0.02Improved
Add rotation prediction as an auxiliary task (ablation)STL-10 classifier · STL-10 hold-out-classaccuracy: 85.77 ± 0.13 -> 89.92 ± 0.08Improved
Add rotation prediction as an auxiliary task (ablation)ImageNet Dog subset classifier with MSP · ImageNet Dog subsetaverage precision: 23.92 ± 0.49 -> 24.66 ± 0.58No clear effect
Add rotation prediction as an auxiliary task (ablation)ImageNet Car subset classifier with MSP · ImageNet Car subsetaverage precision: 21.54 ± 0.62 -> 21.66 ± 0.19No clear effect
Add CPC as an auxiliary task (ablation)ImageNet subset classifier with MSP · ImageNet subsetsaverage precision: Dog 20.84 ± 0.50 -> 21.43 ± 0.63; Car 19.86 ± 0.21 -> 22.21 ± 0.44; Snake 18.20 ± 0.76 -> 18.78 ± 0.40; Spider 22.03 ± 0Mixed
Add CPC as an auxiliary task (ablation)ImageNet subset classifier with ODIN · ImageNet subsetsaverage precision: Dog 22.77 ± 0.74 -> 24.08 ± 0.63; Car 21.42 ± 0.48 -> 23.61 ± 0.57; Snake 18.67 ± 1.07 -> 20.39 ± 0.60; Spider 24.08 ± 0Mixed
Randomly mask a 16 × 16 region within the central 21 × 21 region (ablation)CIFAR-10 classifier · CIFAR-10 hold-out-classaverage precision with MSP: 34.92 ± 0.41 -> 34.41 ± 0.74Hurt
Replace classification-only training with random-center masking (ablation)CIFAR-10 classifier · CIFAR-10 hold-out-classaccuracy: 96.03 ± 0.00 -> 96.27 ± 0.05Improved

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