Shop The Look: Building a Large Scale Visual Shopping System at Pinterest
Not on the map. Why?
Abstract (arXiv)
As online content becomes ever more visual, the demand for searching by visual queries grows correspondingly stronger. Shop The Look is an online shopping discovery service at Pinterest, leveraging visual search to enable users to find and buy products within an image. In this work, we provide a holistic view of how we built Shop The Look, a shopping oriented visual search system, along with lessons learned from addressing shopping needs. We discuss topics including core technology across object detection and visual embeddings, serving infrastructure for realtime inference, and data labeling methodology for training/evaluation data collection and human evaluation. The user-facing impacts of our system design choices are measured through offline evaluations, human relevance judgements, and online A/B experiments. The collective improvements amount to cumulative relative gains of over 160% in end-to-end human relevance judgements and over 80% in engagement. Shop The Look is deployed in production at Pinterest.
Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jun 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 1; 2025: 4; 2026: 1.
12 papers.
- 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representationscited by 24
- 2022e-CLIP: Large-Scale Vision-Language Representation Learning in E-commercecited by 10
- 2023OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Datacited by 9
- 2022Sublinear Time Algorithm for Online Weighted Bipartite Matchingcited by 7
- 2023LRVS-Fashion: Extending Visual Search with Referring Instructionscited by 4
- 2025OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Searchcited by 2
- 2024FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentationcited by 1
- 2021Web-Scale Generic Object Detection at Microsoft Bingcited by 0
- 2025Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendationscited by 0
- 2025Zero-Shot Retrieval for Scalable Visual Search in a Two-Sided Marketplacecited by 0
- 2025Optimizing Product Deduplication in E-Commerce with Multimodal Embeddingscited by 0
- 2026LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Datacited by 0
- 2026LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data30 Jul 2026
- 2025OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search7 Oct 2025
- 2025Optimizing Product Deduplication in E-Commerce with Multimodal Embeddings19 Sep 2025
- 2025Zero-Shot Retrieval for Scalable Visual Search in a Two-Sided Marketplace31 Jul 2025
- 2025Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendations27 May 2025
- 2024FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation12 Apr 2024
- 2023OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data11 Sep 2023
- 2023LRVS-Fashion: Extending Visual Search with Referring Instructions5 Jun 2023
- 2022Sublinear Time Algorithm for Online Weighted Bipartite Matching5 Aug 2022
- 2022e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce1 Jul 2022
- 2021Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations12 Aug 2021
- 2021Web-Scale Generic Object Detection at Microsoft Bing5 Jul 2021