Why do CNNs generalize so poorly to small image transformations?

Re:Why do CNNs generalize so poorly to small image transform... by 317070 on Sunday June 10, 2018 @04:56PM (#17280102)

There are more permutation invariant networks. Look for Bruno or for Neural Statistician. Both of these are RNN's with the exchangeability property. This means inputs and output can be permuted with each other. If you need something with less strong constraints (but still invariant under permutation of the input), there is also Deep Sets.

[ Parent | on HN ]

Re:Why do CNNs generalize so poorly to small image transform... by calebh on Sunday June 10, 2018 @05:51PM (#17280363)

Ah, thanks for the tip. When I'm reading research papers I often find clusters of related papers with the same keywords. Often finding the separate clusters is a difficult challenge, even if you use Google Scholar and follow all the citations.

[ Parent | on HN ]