# Visual Product Graph: Bridging Visual Products And Composite Images For End-to-End Style Recommendations

arXiv: https://arxiv.org/abs/2505.21454 · HTML: https://mlsanity.com/paper/2505.21454/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Exploring the Limits of Weakly Supervised Pretraining](https://mlsanity.com/paper/1805.00932/) (2018)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [Embedding-based Product Retrieval in Taobao Search](https://mlsanity.com/paper/2106.09297/) (2021)
- [Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences](https://mlsanity.com/paper/1509.07473/) (2015)
- [Learning a Unified Embedding for Visual Search at Pinterest](https://mlsanity.com/paper/1908.01707/) (2019)
- [Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations](https://mlsanity.com/paper/2108.05887/) (2021)
- [ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest](https://mlsanity.com/paper/2205.11728/) (2022)
- [Shop The Look: Building a Large Scale Visual Shopping System at Pinterest](https://mlsanity.com/paper/2006.10866/) (2020)
- [Bootstrapping Complete The Look at Pinterest](https://mlsanity.com/paper/2006.10792/) (2020)
- [Evolution of a Web-Scale Near Duplicate Image Detection System](https://mlsanity.com/paper/2209.08433/) (2022)

## Abstract (arXiv)

Retrieving semantically similar but visually distinct contents has been a critical capability in visual search systems. In this work, we aim to tackle this problem with Visual Product Graph (VPG), leveraging high-performance infrastructure for storage and state-of-the-art computer vision models for image understanding. VPG is built to be an online real-time retrieval system that enables navigation from individual products to composite scenes containing those products, along with complementary recommendations. Our system not only offers contextual insights by showcasing how products can be styled in a context, but also provides recommendations for complementary products drawn from these inspirations. We discuss the essential components for building the Visual Product Graph, along with the core computer vision model improvements across object detection, foundational visual embeddings, and other visual signals. Our system achieves a 78.8% extremely similar@1 in end-to-end human relevance evaluations, and a 6% module engagement rate. The "Ways to Style It" module, powered by the Visual Product Graph technology, is deployed in production at Pinterest.