AI Paper Atlas

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

Extremely Simple Activation Shaping for Out-of-Distribution Detection

Andrija Djurisic, Nebojsa Bozanic, Arjun Ashok, Rosanne Liu

ICLR 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 23 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
Prune low-valued activations and binarize the retained activationsResNet-50 with ASH-B@65 · ImageNet OOD averageFPR95: 27.25 -> 22.73Improved
Prune low-valued activations and exponentially scale the retained activationsDenseNet-101 · CIFAR-10 OOD averageFPR95: 20.83 -> 15.05Improved
Prune low-valued activations and exponentially scale the retained activationsDenseNet-101 · CIFAR-100 OOD averageFPR95: 49.72 -> 41.40Improved
Add ASH treatment to the Energy score (ablation)ResNet-50 · ImageNet OOD averageFPR95: 57.47 -> 22.80Improved
Add ASH treatment to ODIN (ablation)ResNet-50 · ImageNet OOD averageFPR95: 50.80 -> 28.59Improved
Add ASH treatment to ReAct (ablation)ResNet-50 · ImageNet OOD averageFPR95: 31.43 -> 24.88Improved
Replace exponential scaling with linear scaling (ablation)ASH-S@90 on ResNet-50 · ImageNet OOD averageFPR95: 22.80 -> 36.72Hurt
Use a global threshold instead of a local, per-input threshold (ablation)ASH-S@90 on ResNet-50 · ImageNet OOD averageFPR95: 22.80 -> 54.74Hurt
Move ASH-S from the penultimate layer to before the last ReLU of the 3rd Block (ablation)ResNet-50 · ImageNet OOD averageFPR95: 22.80 -> 98.51Hurt
Add scaling to pruning-only ASH-P (ablation)ASH-S on ResNet-50 · ImageNet OOD averageFPR95: 50.32 -> 22.80Improved
Randomize retained activations instead of binarizing or scaling them (ablation)ASH-RAND@65 on ResNet-50 · ImageNet OOD averageFPR95: 22.73 -> 45.37Hurt
Increase pruning from 65% to 90% with ASH-S (ablation)ResNet-50 · ImageNet validationTop-1 accuracy: 76.01\% -> 74.98\%Hurt

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