Show HN: Cornea AI – Using Deep Learning to Predict Photo Popularity

Re:Show HN: Cornea AI – Using Deep Learning to Predict Photo... by have_faith on Thursday August 24, 2017 @05:54AM (#15088805)

Could you plug this into one of those image generation algorithms and generate a potentially popular image from scratch?

Side note: I can imagine high speed ad networks in the future using this to deliver custom images in real time to users based on their profiles. Tweaked of course based on the interests of their extended network and the likelihood of going viral within that network.

[ Parent | on HN ]

Re:Show HN: Cornea AI – Using Deep Learning to Predict Photo... by muktabh on Thursday August 24, 2017 @06:03AM (#15088835)

Hi, That can be done, but image generation algorithms require a bit more time to be good enough for such a thing. Two major bottlenecks (I am assuming you are talking about GANs) are: 1. The algorithms are still not too good for hi res images. 2. The algorithms work very well on images where fine grained features are not that important. (For example images of nature), but they introduce unwanted features otherwise (Eyes looking other ways etc.). We might be all ready by next ICLR/NIPS though, cannot say.

[ Parent | on HN ]