Mining Mid-level Visual Patterns with Deep CNN Activations — mentioned by cdoersch

Thu, 16 Aug 2018 11:16:17 GMT

Wow--didn't expect my old paper to re-surface in 2018. Besides being a neat visualization, one remarkable thing (to me) is that this is one of the few computer vision tasks where the state-of-the-art is still the old hand-designed descriptors--specifically HOG. The attempts to re-do this work with deep learning haven't worked so well. The closest I know is https://arxiv.org/abs/1506.06343 , which I've never even seen applied to cities. The problem is actually that deep nets have too much invariance: they can classify whether a facade is in Paris or not, but there's no easy way to separate out…

Paper and discussion history. A mention is not an endorsement.

Mining Mid-level Visual Patterns with Deep CNN Activations · HackerPapers discussions

Mining Mid-level Visual Patterns with Deep CNN Activations — mentioned by cdoersch