AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation

Hermann Blum, Paul-Edouard Sarlin, Juan I. Nieto, Roland Siegwart, César Cadena

IJCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 169 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 input noise preprocessing (ablation)Learned Embedding Density · FS Static testAP: 52.5 -> 55.4Improved
increase kNN neighbors from 1 to 20 (ablation)kNN Embedding density · FS Lost & Found validationAP: 42.3 -> 52.2Improved
increase kNN neighbors for class-based density from 5 to 100 (ablation)kNN relative class density · FS Static validationAP: 5.4 -> 9.9Improved
aggregate layers with minimum NLL instead of a single layer (ablation)Learned Embedding Density · FS StaticAP: 40.9 -> 62.1Improved
aggregate layers with logistic regression instead of single layer (ablation)Learned Embedding Density · FS StaticAP: 40.9 -> 57.2Improved
use minimum NLL instead of logistic regression aggregation (ablation)Learned Embedding Density · FS Lost & FoundFPR95: 24.4 -> 47.2Hurt
use softmax entropy instead of max-probability (ablation)Softmax baseline · FS StaticAP: 12.9 -> 15.4Improved
train with OoD data (void classifier) instead of no OoD trainingDeepLabv3+ softmax baseline · FS StaticAP: 12.9 -> 45.0Improved
train with special OoD losses (Outlier Head) versus unmodified modelDeepLabv3+ · CityscapesmIoU: 80.3 -> 77.3Hurt
use Bayesian predictive entropy instead of mutual informationBayesian DeepLab · FS MisclassificationAP: 70.4 -> 73.8Improved
use softmax max-probability for misclassification instead of anomaly detectionSoftmax · FS Lost & Found vs FS MisclassificationAP: 1.8 -> 67.4Improved
add blended in-distribution objects to FS Web (Jan 20)embedding-based methods · FS WebAPNo 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