SIR: Similar Image Retrieval For Product Search In E-commerce
2020 · Theban Stanley, Nihar Vanjara, Yanxin Pan, et al.
Abstract
We present a similar image retrieval (SIR) platform that is used to quickly discover visually similar products in a catalog of millions. Given the size, diversity, and dynamism of our catalog, product search poses many challenges. It can be addressed by building supervised models to tagging product images with labels representing themes and later retrieving them by labels. This approach suffices for common and perennial themes like "white shirt" or "lifestyle image of TV". It does not work for new themes such as "e-cigarettes", hard-to-define ones such as "image with a promotional badge", or the ones with short relevance span such as "Halloween costumes". SIR is ideal for such cases because it allows us to search by an example, not a pre-defined theme. We describe the steps - embedding computation, encoding, and indexing - that power the approximate nearest neighbor search back-end. We also highlight two applications of SIR. The first one is related to the detection of products with va
Authors
(none)
Tags
Stats
Related papers
- PRISM: Product Retrieval In Shopping Carts Using Hybrid Matching (2025)0.00
- Visually Similar Products Retrieval For Shopsy (2022)2.26
- Searching For Apparel Products From Images In The Wild (2019)0.00
- Learning Image Information For Ecommerce Queries (2019)0.00
- Multimodal Semantic Retrieval For Product Search (2025)3.58
- Unified Vision-language Representation Modeling For E-commerce Same-style Products Retrieval (2023)6.34
- Large-scale Real-time Personalized Similar Product Recommendations (2020)0.00
- Visual Product Search Benchmark (2026)0.00