eProduct Visual Search Challenge 2021

Overview

Large-scale product recognition is one of the major applications of computer vision and machine learning in the e-commerce domain. Since the number of products is typically much larger than the number of categories of products, image-based product recognition is often cast as a visual search rather than a classification problem. It is also one of the instances of super fine-grained recognition, where there are many products with slight or subtle visual differences. It has always been a challenge to create a benchmark dataset for training and evaluation on various visual search solutions in a real-world setting. This motivated the creation of eProduct, a large-scale benchmark dataset for product recognition challenges in a visual search setting. The training set contains 1.3M+ listing images, with titles and hierarchical category labels. The evaluation set includes 5K query and 1.1M+ index images for visual search evaluation. Please refer to the eProduct visual search challenge on EvalAI for additional dataset details and participation information.

Competition

Start Date - April 16, 2021

End Date - June 6th AM, 2021

Competition URL - https://eval.ai/web/challenges/challenge-page/888/overview

Organizers

Jiangbo Yuan (eBay Inc.,), An-Ti Chiang (eBay Inc.,), Wen Tang (eBay Inc.,), Antonio Haro (eBay Inc.,)

Acknowledgements

The eProduct Visual Search Challenge 2021 is sponsored by eBay Inc.. We are grateful to many colleagues who provided help launching this challenge. Special thanks to Balamurali Meduri for suggestions and generous support, and Bradley Sanders for legal support.