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

TL;DR

This paper introduces a triplet loss-based embedding learning method with online sampling for product image retrieval, achieving state-of-the-art results on fashion datasets and competitive performance on product datasets.

Contribution

It presents a novel online sampling approach for triplet loss training tailored for e-commerce image retrieval tasks.

Findings

Outperforms state-of-the-art on DeepFashion dataset.

Achieves competitive results on Stanford Online Products dataset.

Effective for content-based image retrieval in e-commerce.

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.