Scaling Cross-Domain Content-Based Image Retrieval for E-commerce Snap and Search Application

TL;DR

This paper presents a scalable cross-domain image retrieval system for e-commerce that combines visual search and classification, addressing large-scale data and real-world application challenges.

Contribution

It introduces a cascade-based approach integrating visual search and classification to improve scalability and performance in cross-domain e-commerce image retrieval.

Findings

Effective handling of large-scale e-commerce image data

Improved ranking accuracy in real-world applications

Reduced latency in image retrieval processes

Abstract

In this industry talk at ECIR 2022, we illustrate how we approach the main challenges from large scale cross-domain content-based image retrieval using a cascade method and a combination of our visual search and classification capabilities. Specifically, we present a system that is able to handle the scale of the data for e-commerce usage and the cross-domain nature of the query and gallery image pools. We showcase the approach applied in real-world e-commerce snap and search use case and its impact on ranking and latency performance.