arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.07058cs.CV
收藏

概念检索——是什么以及如何实现?

Concept Retrieval -- What and How?

Technion(技术离子大学)

Ori Nizan, Oren Shrout, Ayellet Tal

AI总结:

本文针对共享核心概念的图像检索任务,正式定义问题并设计评估指标,基于嵌入空间邻域特性与双峰高斯分布建模提出新方法,经多类评估验证有效并开源实现。

摘要:

概念既可以指代具体想法,也可以指代抽象想法。给定一张输入图像,本文旨在检索与其共享核心概念的其他图像,捕捉其潜在叙事的相关维度,这一任务超越了侧重视觉或语义相似性的传统检索与聚类方法。本文正式定义了该问题,梳理了核心要求,并引入了适配的评估指标。基于两个关键观察,本文提出了一种新方法:(1)尽管嵌入空间中的每个近邻通常与查询图像共享至少一个概念,但并非所有近邻之间都共享同一概念;(2)使用双峰高斯分布对该邻域建模可挖掘出有意义的结构,助力概念识别。定性、定量以及人工评估均证实了该方法的有效性,相关实现包已发布至PyPI:https://pypi.org/project/coret/。

英文摘要:

A concept may reflect either a concrete or abstract idea. Given an input image, this paper seeks to retrieve other images that share its central concepts, capturing aspects of the underlying narrative. This goes beyond conventional retrieval or clustering methods, which emphasize visual or semantic similarity. We formally define the problem, outline key requirements, and introduce appropriate evaluation metrics. We propose a novel approach grounded in two key observations: (1) While each neighbor in the embedding space typically shares at least one concept with the query, not all neighbors necessarily share the same concept with one another. (2) Modeling this neighborhood with a bimodal Gaussian distribution uncovers meaningful structure that facilitates concept identification. Qualitative, quantitative, and human evaluations confirm the effectiveness of our approach. See the package on PyPI: https://pypi.org/project/coret/

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑