Jordi Pont-Tuset bio photo

Jordi Pont-Tuset

I'm from a small town near Girona, Catalunya. Currently in Zürich, Switzerland. Passionate about computer vision, technology, running, and mountains.

Twitter   G. Scholar LinkedIn Github e-Mail Google+

It’s that time of the year when a major vision conference releases the papers to the public, so it’s time to check how deep learning is doing in their titles.

At ICCV 2017, we realized that GANs were growing strong, and before we did a set of posts of the deep learning saga.

Let’s update the plots to CVPR 2018, as always, using the XKCD style, as described in this blog post, but this time putting all trends together:

So, general deep-learning keywords are getting out of fashion (we take them for granted), but GANs are no longer such a minority (8\%!). LSTM, on the other hand, cannot keep up. Will GANs catch up with general deep learning?

Are GANs the new Deep?