Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287664043> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4287664043 abstract "Computer Vision practitioners must thoroughly understand their model's performance, but conditional evaluation is complex and error-prone. In biometric verification, model performance over continuous covariates---real-number attributes of images that affect performance---is particularly challenging to study. We develop a generative model of the match and non-match score distributions over continuous covariates and perform inference with modern Bayesian methods. We use mixture models to capture arbitrary distributions and local basis functions to capture non-linear, multivariate trends. Three experiments demonstrate the accuracy and effectiveness of our approach. First, we study the relationship between age and face verification performance and find previous methods may overstate performance and confidence. Second, we study preprocessing for CNNs and find a highly non-linear, multivariate surface of model performance. Our method is accurate and data efficient when evaluated against previous synthetic methods. Third, we demonstrate the novel application of our method to pedestrian tracking and calculate variable thresholds and expected performance while controlling for multiple covariates." @default.
- W4287664043 created "2022-07-25" @default.
- W4287664043 creator A5024169695 @default.
- W4287664043 creator A5027477070 @default.
- W4287664043 creator A5051029455 @default.
- W4287664043 creator A5091513740 @default.
- W4287664043 date "2020-09-20" @default.
- W4287664043 modified "2023-09-26" @default.
- W4287664043 title "Modeling Score Distributions and Continuous Covariates: A Bayesian Approach" @default.
- W4287664043 doi "https://doi.org/10.48550/arxiv.2009.09583" @default.
- W4287664043 hasPublicationYear "2020" @default.
- W4287664043 type Work @default.
- W4287664043 citedByCount "0" @default.
- W4287664043 crossrefType "posted-content" @default.
- W4287664043 hasAuthorship W4287664043A5024169695 @default.
- W4287664043 hasAuthorship W4287664043A5027477070 @default.
- W4287664043 hasAuthorship W4287664043A5051029455 @default.
- W4287664043 hasAuthorship W4287664043A5091513740 @default.
- W4287664043 hasBestOaLocation W42876640431 @default.
- W4287664043 hasConcept C107673813 @default.
- W4287664043 hasConcept C119043178 @default.
- W4287664043 hasConcept C119857082 @default.
- W4287664043 hasConcept C124101348 @default.
- W4287664043 hasConcept C154945302 @default.
- W4287664043 hasConcept C161584116 @default.
- W4287664043 hasConcept C184297639 @default.
- W4287664043 hasConcept C2776214188 @default.
- W4287664043 hasConcept C41008148 @default.
- W4287664043 hasConceptScore W4287664043C107673813 @default.
- W4287664043 hasConceptScore W4287664043C119043178 @default.
- W4287664043 hasConceptScore W4287664043C119857082 @default.
- W4287664043 hasConceptScore W4287664043C124101348 @default.
- W4287664043 hasConceptScore W4287664043C154945302 @default.
- W4287664043 hasConceptScore W4287664043C161584116 @default.
- W4287664043 hasConceptScore W4287664043C184297639 @default.
- W4287664043 hasConceptScore W4287664043C2776214188 @default.
- W4287664043 hasConceptScore W4287664043C41008148 @default.
- W4287664043 hasLocation W42876640431 @default.
- W4287664043 hasOpenAccess W4287664043 @default.
- W4287664043 hasPrimaryLocation W42876640431 @default.
- W4287664043 hasRelatedWork W2044158 @default.
- W4287664043 hasRelatedWork W2777878 @default.
- W4287664043 hasRelatedWork W4272086 @default.
- W4287664043 hasRelatedWork W4505823 @default.
- W4287664043 hasRelatedWork W695875 @default.
- W4287664043 hasRelatedWork W760780 @default.
- W4287664043 hasRelatedWork W8021486 @default.
- W4287664043 hasRelatedWork W9177359 @default.
- W4287664043 hasRelatedWork W9329549 @default.
- W4287664043 hasRelatedWork W722847 @default.
- W4287664043 isParatext "false" @default.
- W4287664043 isRetracted "false" @default.
- W4287664043 workType "article" @default.