A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Piérard, Sébastien, Deliège, Adrien, Halin, Anaïs, Van Droogenbroeck, Marc
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914415290351616
author Piérard, Sébastien
Deliège, Adrien
Halin, Anaïs
Van Droogenbroeck, Marc
author_facet Piérard, Sébastien
Deliège, Adrien
Halin, Anaïs
Van Droogenbroeck, Marc
contents Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distribution of scenarios encountered. For example, in computer vision, the input data provided to image analysis methods depend on the type of sensor used, its location, and the scene content. However, a crucial difficulty remains: can we predict which entities will perform best in a new domain based on assessments on known domains, without having to carry out new and costly evaluations? This paper presents an original methodology to address this question, in a leave-one-domain-out fashion, for various application-specific preferences. We illustrate its use with 30 strategies to predict the rankings of 40 entities (unsupervised background subtraction methods) on 53 domains (videos).
format Preprint
id arxiv_https___arxiv_org_abs_2505_15595
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
Piérard, Sébastien
Deliège, Adrien
Halin, Anaïs
Van Droogenbroeck, Marc
Performance
Computer Vision and Pattern Recognition
Frequently, multiple entities (methods, algorithms, procedures, solutions, etc.) can be developed for a common task and applied across various domains that differ in the distribution of scenarios encountered. For example, in computer vision, the input data provided to image analysis methods depend on the type of sensor used, its location, and the scene content. However, a crucial difficulty remains: can we predict which entities will perform best in a new domain based on assessments on known domains, without having to carry out new and costly evaluations? This paper presents an original methodology to address this question, in a leave-one-domain-out fashion, for various application-specific preferences. We illustrate its use with 30 strategies to predict the rankings of 40 entities (unsupervised background subtraction methods) on 53 domains (videos).
title A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
topic Performance
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.15595