arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04652cs.CVcs.IRcs.LG
收藏

基于三重损失和在线抽样的产品视觉搜索的学习嵌入

Learning Embeddings for Product Visual Search with Triplet Loss and Online Sampling

Yahoo Research(雅虎研究院)

Eric Dodds, Huy Nguyen, Simao Herdade, Jack Culpepper, Andrew Kae, Pierre Garrigues

摘要:

在本文中,我们提出了学习嵌入功能的电子商务领域内的基于内容的图像检索使用的三重损失和在线采样方法,从一个minibatch构建三胞胎。我们将我们的方法与几个强大的基线以及DeepFashion和Stanford Online Product数据集的最新作品进行了比较。我们的方法在DeepFashion数据集上的表现明显优于最先进的方法。通过修改以支持从单个产品类别中采样小批量,与斯坦福在线产品数据集的最新技术相比,相同的方法显示出具有竞争力的结果。

英文摘要:

In this paper, we propose learning an embedding function for content-based image retrieval within the e-commerce domain using the triplet loss and an online sampling method that constructs triplets from within a minibatch. We compare our method to several strong baselines as well as recent works on the DeepFashion and Stanford Online Product datasets. Our approach significantly outperforms the state-of-the-art on the DeepFashion dataset. With a modification to favor sampling minibatches from a single product category, the same approach demonstrates competitive results when compared to the state-of-the-art for the Stanford Online Products dataset.

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。

↑