KS(conf): a light-weight test if a multiclass classifier operates outside of its specifications

DOI10.1007/s11263-019-01232-xzbMath1478.62178OpenAlexW2979815249WikidataQ92097323 ScholiaQ92097323MaRDI QIDQ2193578

Christoph H. Lampert, Rémy Sun

Publication date: 20 August 2020

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-019-01232-x

zbMATH Keywords

specificationsmulti-class classificationdeep convolutional networksdistribution shift

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07) Machine vision and scene understanding (68T45)

Uses Software

• GitHub
• k.c
• SqueezeNet
• GNU parallel
• iCaRL
• MobileNets

Cites Work

• Unnamed Item
• Unnamed Item
• Optimal detection of a change in distribution
• A theory of learning from different domains
• A survey of outlier detection methodologies
• Overcoming catastrophic forgetting in neural networks
• A survey on concept drift adaptation
• The Kolmogorov-Smirnov Test for Goodness of Fit

This page was built for publication: KS(conf): a light-weight test if a multiclass classifier operates outside of its specifications