AI Paper Atlas

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

Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation

Robin Chan, Matthias Rottmann, Hanno Gottschalk

ICCV 2021 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 170 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 OoD training with entropy maximization on COCO (ablation)DeepLabv3+ WideResNet38 baseline · LostAndFound pixel-wiseAUPRC: 0.46 -> 0.76Improved
add OoD training with entropy maximization on COCO (ablation)DeepLabv3+ WideResNet38 baseline · Fishyscapes Val pixel-wiseAUPRC: 0.28 -> 0.81Improved
add OoD training with entropy maximization (ablation)DualGCNNet · LostAndFound pixel-wiseAUPRC: 0.36 -> 0.51Improved
add OoD training with entropy maximization (ablation)DualGCNNet · Fishyscapes Val pixel-wiseAUPRC: 0.07 -> 0.38Improved
add OoD training with entropy maximization (ablation)DeepLabv3+ WideResNet38 · LostAndFound pixel-wiseFPR95: 0.35 -> 0.09Improved
add OoD training with entropy maximization (ablation)DeepLabv3+ WideResNet38 · Cityscapes valmIoU: 0.90 -> 0.89Hurt
add OoD training with entropy maximization (ablation)DualGCNNet · Cityscapes valmIoU: 0.80 -> 0.76Hurt
lower entropy threshold to t=0.2 for OoD prediction (ablation)DeepLabv3+ WideResNet38 baseline · Cityscapes valmIoU: 0.05 baseline and 0.03 re-trained mIoU decreaseHurt
add a meta classifier on top of entropy thresholding (ablation)OoD-trained model at t=0.3 · LostAndFound segment-wiseF1: 0.26 -> 0.82Improved
add a meta classifier on top of entropy thresholding (ablation)baseline model at t=0.3 · LostAndFound segment-wiseF1: 0.28 -> 0.79Improved
add OoD training (ablation)baseline + meta classifier at t=0.7 · LostAndFound meta classificationAUPRC: 0.5283 -> 0.7185Improved
add OoD training (ablation)baseline + meta classifier at t=0.1 · LostAndFound meta classificationAUPRC: 0.9993 -> 0.9993No clear effect

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