Products-10K: A Large-scale Product Recognition Dataset

TL;DR

This paper introduces Products-10K, a large, human-labeled dataset of 10,000 fine-grained SKU product images designed to advance product recognition accuracy in e-commerce applications.

Contribution

The paper presents a new large-scale, human-labeled product dataset and offers practical tips for improving fine-grained product recognition models.

Findings

Dataset contains 10,000 SKU-level products.

Provides effective strategies for product recognition.

Facilitates development of high-accuracy recognition systems.

Abstract

With the rapid development of electronic commerce, the way of shopping has experienced a revolutionary evolution. To fully meet customers' massive and diverse online shopping needs with quick response, the retailing AI system needs to automatically recognize products from images and videos at the stock-keeping unit (SKU) level with high accuracy. However, product recognition is still a challenging task, since many of SKU-level products are fine-grained and visually similar by a rough glimpse. Although there are already some products benchmarks available, these datasets are either too small (limited number of products) or noisy-labeled (lack of human labeling). In this paper, we construct a human-labeled product image dataset named "Products-10K", which contains 10,000 fine-grained SKU-level products frequently bought by online customers in JD.com. Based on our new database, we also introduced several useful tips and tricks for fine-grained product recognition. The products-10K dataset is available via https://products-10k.github.io/.