Pinterest Introduces the Future of Visual Search

The popular social photo sharing site is adding the ability for people to take a photo of things in the real-world and get recommendations for similar products on Pinterest. For example, If you take a photo of a room with a purse and a lamp on a table that you like, Pinterest will show you results for all three items.

Using TITAN X GPUs and the Caffe deep learning framework, the team trained their convolutional neural networks on millions of images uploaded by Pinterest users and then used GPUs in the Amazon cloud to both detect and classify objects in real-time.

Automatic Object Detection, multiple objects - GIF

TechCrunch mentions that the new visual search capability could help Pinterest evolve into an online shopping experience with the ability to tap into users at all moments in the purchasing process, from becoming aware of certain products and brands, to searching for them and declaring interest, and then actually buying them.

The visual search functionality will roll out to Pinterest users in the next few weeks.


About Brad Nemire

Brad Nemire
Brad Nemire is on the Developer Marketing team and loves reading about all of the fascinating research being done by developers using NVIDIA GPUs. Reach out to Brad on Twitter @BradNemire and let him know how you’re using GPUs to accelerate your research. Brad graduated from San Diego State University and currently resides in San Jose, CA. Follow @BradNemire on Twitter