Learning A Unified Embedding For Visual Search At Pinterest
2019 · Andrew Zhai, Hao-Yu Wu, Eric Tzeng, et al.
Abstract
At Pinterest, we utilize image embeddings throughout our search and recommendation systems to help our users navigate through visual content by powering experiences like browsing of related content and searching for exact products for shopping. In this work we describe a multi-task deep metric learning system to learn a single unified image embedding which can be used to power our multiple visual search products. The solution we present not only allows us to train for multiple application objectives in a single deep neural network architecture, but takes advantage of correlated information in the combination of all training data from each application to generate a unified embedding that outperforms all specialized embeddings previously deployed for each product. We discuss the challenges of handling images from different domains such as camera photos, high quality web images, and clean product catalog images. We also detail how to jointly train for multiple product objectives and how t
Authors
(none)
Tags
Stats
Related papers
- Deep Learning Based Large Scale Visual Recommendation And Search For E-commerce (2017)0.00
- Pinclip: Large-scale Foundational Multimodal Representation At Pinterest (2026)0.00
- Univse: Robust Visual Semantic Embeddings Via Structured Semantic Representations (2019)0.00
- Decoupled Entity Representation Learning For Pinterest Ads Ranking (2025)0.00
- Learning Embeddings For Product Visual Search With Triplet Loss And Online Sampling (2018)0.00
- Learning To Embed Semantic Similarity For Joint Image-text Retrieval (2022)7.50
- Visual Product Search Benchmark (2026)0.00
- Unified Embedding Based Personalized Retrieval In Etsy Search (2023)2.26