AI Paper Atlas

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

LINe: Out-of-Distribution Detection by Leveraging Important Neurons

Yong Hyun Ahn, Gyeong-Moon Park, Seong Tae Kim

CVPR 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 31 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 LINe instead of DICE + ReActDenseNet · CIFAR-10 (six OOD datasets, average)FPR95: 16.48 -> 14.71Improved
Use LINe instead of DICE + ReActDenseNet · CIFAR-100 (six OOD datasets, average)FPR95: 49.57 -> 35.67Improved
Use LINe instead of DICE + ReActResNet-50 · ImageNet (four OOD datasets, average)FPR95: 27.25 -> 20.70Improved
Add activation clipping (ablation)Energy OOD scoring on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 58.41 -> 35.40Improved
Add activation pruning to activation clipping (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 26.88 -> 20.70Improved
Add weight pruning to activation clipping (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 23.19 -> 20.70Improved
Set activation clipping threshold δ to 0.8 rather than no clipping (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 44.88 -> 20.70Improved
Lower clipping threshold from δ = 0.8 to δ = 0.1 (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 20.70 -> 41.18Hurt
Raise clipping threshold from δ = 0.8 to δ = 2.0 (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 20.70 -> 31.88Hurt
Set pruning percentiles p_w = 10 and p_a = 10 (ablation)LINe on ResNet-50 · ImageNet (four OOD datasets, average)FPR95: 27.64 -> 20.70Improved
Replace Taylor with IntGrad for Shapley approximation (ablation)LINe on DenseNet and ResNet-50 · CIFAR-10, CIFAR-100, and ImageNetFPR95: 14.71 -> 14.71; 35.67 -> 35.67; 20.70 -> 20.70No clear effect

Later papers that compared with this method

4 later accepted papers report Line as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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