Guardado en:
Detalles Bibliográficos
Autores principales: Zhao, Jinjin, Shaowang, Ted, Sintos, Stavos, Krishnan, Sanjay
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.17686
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916262804717568
author Zhao, Jinjin
Shaowang, Ted
Sintos, Stavos
Krishnan, Sanjay
author_facet Zhao, Jinjin
Shaowang, Ted
Sintos, Stavos
Krishnan, Sanjay
contents Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug. Current model explanation system are very good at giving literal explanations of behavior in terms of pixel contributions but cannot integrate information about the physical or systems processes that might influence a prediction. This paper introduces the idea that a simple form of causal reasoning, called a regression discontinuity design, can be used to associate changes in multiple key performance indicators to physical real world phenomena to give users a more actionable set of video analytics explanations. We overview the system architecture and describe a vision of the impact that such a system might have.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17686
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Causal Physical Error Discovery in Video Analytics Systems
Zhao, Jinjin
Shaowang, Ted
Sintos, Stavos
Krishnan, Sanjay
Computer Vision and Pattern Recognition
Video analytics systems based on deep learning models are often opaque and brittle and require explanation systems to help users debug. Current model explanation system are very good at giving literal explanations of behavior in terms of pixel contributions but cannot integrate information about the physical or systems processes that might influence a prediction. This paper introduces the idea that a simple form of causal reasoning, called a regression discontinuity design, can be used to associate changes in multiple key performance indicators to physical real world phenomena to give users a more actionable set of video analytics explanations. We overview the system architecture and describe a vision of the impact that such a system might have.
title Towards Causal Physical Error Discovery in Video Analytics Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17686