Learning Embeddings For Product Visual Search With Triplet Loss And Online Sampling

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydodds2018learning

Related papers

• Learning A Unified Embedding For Visual Search At Pinterest (2019)10.85
• Improved Embeddings With Easy Positive Triplet Mining (2019)15.06
• Sampling Matters In Deep Embedding Learning (2017)20.43
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• Multitask Text-to-visual Embedding With Titles And Clickthrough Data (2019)0.00
• Unified Embedding Based Personalized Retrieval In Etsy Search (2023)2.26
• Fast Training Of Triplet-based Deep Binary Embedding Networks (2016)14.62
• Visually Similar Products Retrieval For Shopsy (2022)2.26