The first feature, Find It On eBay, allows users to “share” an image they find on the web or through a social platform with eBay. Ebay will then find listings that are similar. The second feature, Image Search, does the same thing using images that users take and have stored in their phones’ camera roll.

Ebay explained the artificial intelligence and machine learning technology behind these two new features:

When you upload images to run Find It On eBay and Image Search, we use a deep learning model called a convolutional neural network to process the images. The output of the model gives us a representation of your image that we can use to compare to the images of the live listings on eBay. Then, we rank the items based on visual similarity and use our open-source Kubernetes platform to quickly bring these results to you, wherever you are in the world.

Ebay says that its technology will learn and improve as more people use it.

The rise of visual search

While it’s not clear that visual search will be enough of a draw to respark growth, the company is not the only one using similar technologies to enable visual search.

For example, popular social platform Pinterest started rolling out visual search functionality in 2015 and this year felt confident enough in its efficacy to apply it to its ads.

“Until now we’ve only applied the visual discovery tech to the organic consumer facing products,” Pinterest president Tim Kendall explained at the TechCrunch Disrupt conference in New York in May. “But the news is we’re now applying it to ads. Think about Pinterest, we have a depth and breadth of visual signals on products and services. We’ve got all that information, we have all these Pins, and the way that people navigate those pins is very visual.

“We leveraged the way people actually use Pinterest. We can identify colors, shapes, textures. We’re able to understand the combined affect people find appealing, even when it can’t be communicated in words.”

Pinterest is in good company. The world’s largest search engine, Google, unveiled a new visual search technology of its own this year. Google Lens has been integrated into Google Photos and Assistant and can be used to help users identify what’s in their photos and videos and connect them to relevant resources. The ecommerce applications of this are obvious.

That explains why retailers such as Target, ASOS and Neiman Marcus have invested in creating their own visual search technologies.

While consumer use of these technologies is still nascent, given the visual nature of the web we can expect to see visual search become an increasingly important area for innovation among retailers, marketplaces, social platforms and search providers.

Those with the best technology and greatest success in encouraging users to search and shop visually could find that they have a real advantage in the years to come as studies have demonstrated that visual technologies are most widely adopted by millennials and Gen Z consumers.