![\"\"](\"http:\/\/sicv.activearchives.org\/logbook\/wp-content\/uploads\/2017\/10\/ebay-image-search.jpg\")
<\/p>\n<\/p>\n
The company explains it\u2019s using two core parts of artificial intelligence \u2013 computer vision and deep learning \u2013 to power these new features. When images are uploaded to eBay, it uses a deep learning model called a convolutional neural network to process the images. The images are compared to the site\u2019s live listings, ranked based on visual similarity, then returned quickly using eBay\u2019s open-source Kubernetes platform.<\/p>\n
Although visual search is a trendy new way to shop online, its overall usefulness remains unproven in the long run. Retailers aren\u2019t releasing stats about how many image searches have actually translated into sales, and arguably, the results can be hit or miss.<\/p>\n
One of the problems is that when you\u2019re looking at a fashion item in a photo, many times you want to find something just like it \u2013 not something only \u201cvisually similar.\u201d<\/p>\n
That is, there are times you just want a small, red handbag with a gold chain and any ol\u2019 handbag of this nature will do; then there are times when you want the exact handbag you\u2019re frothing over right now, or something nearly identical.<\/p><\/blockquote>\n