Once more, let’s plot the evolution of deep learning in the major vision conferences.
Here you can check the previous posts of the saga.
Here the plot using XKCD style, as described in this blog post, where again we separate the two conferences, as introduced in my previous post.
We see that the presence of these keywords is still growing in ECCV and ICCV, with CVPR slightly ahead; but saturating in both.
What about the new kids in class (LSTMs and GANs)?
Nice boost! They’re already in the title of 4% of the papers, not bad. Will they reach the 25% of the generic deep learning?