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 2108.12992cs.LGcs.CV
收藏

SHIFT15M:具有多个分布偏移的集对集匹配的时尚特定数据集

SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts

ZOZO Research(ZOZO研究院)

Masanari Kimura, Takuma Nakamura, Yuki Saito

摘要:

本文讨论了集对集匹配问题,它涉及到基于某些标准匹配两个不同的项目集,特别是在高维项目的情况下,如图像。虽然神经网络已经被应用于解决这个问题,但大多数基于机器学习的方法都假设训练数据和测试数据遵循相同的分布,这在现实世界中并不总是正确的。为了解决这一限制,我们引入了SHIFT 15 M,这是一个数据集,当数据分布在训练和测试之间发生变化时,可用于评估集对集匹配模型。我们进行基准实验,证明性能下降的幼稚方法由于分布偏移。此外,我们还提供了以简单的方式处理SHIFT 15 M数据集的软件,该软件的URL将在本文发表后提供。我们相信,建议的SHIFT 15 M数据集提供了一个宝贵的资源,评估集到集匹配模型下的分布偏移。

英文摘要:

This paper addresses the problem of set-to-set matching, which involves matching two different sets of items based on some criteria, especially in the case of high-dimensional items like images. Although neural networks have been applied to solve this problem, most machine learning-based approaches assume that the training and test data follow the same distribution, which is not always true in real-world scenarios. To address this limitation, we introduce SHIFT15M, a dataset that can be used to evaluate set-to-set matching models when the distribution of data changes between training and testing. We conduct benchmark experiments that demonstrate the performance drop of naive methods due to distribution shift. Additionally, we provide software to handle the SHIFT15M dataset in a simple manner, with the URL for the software to be made available after publication of this manuscript. We believe proposed SHIFT15M dataset provide a valuable resource for evaluating set-to-set matching models under the distribution shift.

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。

↑