提出方法预测新领域表现排名，避免重复测试
A Methodology to Evaluate Strategies Predicting Rankings on Unseen Domains
- 基于留一域外策略，从已知领域推断新领域表现
- 在53个视频域上验证40种方法排名预测效果
- 适合需要跨域评估的算法选型与部署场景
许多任务可开发多种方法并在不同数据分布的领域中应用。例如计算机视觉中，图像分析方法的输入数据受传感器类型、位置和场景内容影响。关键挑战在于：能否仅凭已知领域的评估结果，预测新领域中各方法的最佳表现，而无需进行昂贵的新测试？本文提出一种新方法，以留一域外方式，针对特定应用偏好，评估多个策略对未知领域排名的预测能力。通过30种策略对40种无监督背景分割方法在53个视频域上的排名预测进行验证。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。