arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.14932cs.CVcs.LG
收藏

归因视觉相似性学习

Attributable Visual Similarity Learning

Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology(北京国家信息科学与技术研究中心)

Borui Zhang, Wenzhao Zheng, Jie Zhou, Jiwen Lu

摘要:

本文提出了一个可归因的视觉相似性学习(AVSL)框架,更准确和可解释的图像之间的相似性度量。大多数现有的相似性学习方法通过利用距离度量将每个样本映射到嵌入空间中的单个点(例如,马氏距离(Mahalanobis distance)。受人类语义相似性认知的启发,我们提出了一种广义的相似性学习范式,用图来表示两幅图像之间的相似性,然后据此推断整体相似性。此外,我们建立了一个自底向上的相似性构造和自顶向下的相似性推理框架,以推断基于语义层次一致性的相似性。我们首先确定不可靠的较高级别的相似性节点,然后使用最连贯的相邻的较低级别的相似性节点,同时保留痕迹的相似性属性,以纠正它们。在CUB-200-2011、Cars 196和Stanford Online Products数据集上进行的大量实验表明,与现有的深度相似性学习方法相比,我们的框架有了显著的改进,并验证了我们框架的可解释性。代码可在https://github.com/zbr17/AVSL上获得。

英文摘要:

This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity learning methods exacerbate the unexplainability by mapping each sample to a single point in the embedding space with a distance metric (e.g., Mahalanobis distance, Euclidean distance). Motivated by the human semantic similarity cognition, we propose a generalized similarity learning paradigm to represent the similarity between two images with a graph and then infer the overall similarity accordingly. Furthermore, we establish a bottom-up similarity construction and top-down similarity inference framework to infer the similarity based on semantic hierarchy consistency. We first identify unreliable higher-level similarity nodes and then correct them using the most coherent adjacent lower-level similarity nodes, which simultaneously preserve traces for similarity attribution. Extensive experiments on the CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate significant improvements over existing deep similarity learning methods and verify the interpretability of our framework. Code is available at https://github.com/zbr17/AVSL.

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。

↑