Visual Search at Pinterest
This work enables small teams to implement visual search in commercial applications, though it is incremental as it applies existing tools to a new domain.
The paper tackled building a cost-effective, large-scale visual search system using distributed platforms and open-source tools, showing that it improves user engagement in content recommendation at Pinterest.
We demonstrate that, with the availability of distributed computation platforms such as Amazon Web Services and open-source tools, it is possible for a small engineering team to build, launch and maintain a cost-effective, large-scale visual search system with widely available tools. We also demonstrate, through a comprehensive set of live experiments at Pinterest, that content recommendation powered by visual search improve user engagement. By sharing our implementation details and the experiences learned from launching a commercial visual search engines from scratch, we hope visual search are more widely incorporated into today's commercial applications.