Re:ImageNet-trained CNNs are biased towards texture (2019)
by mbeex on Monday April 20, 2020 @04:16AM
(#22922111)
I think, this is one of the reasons to use much more video-based training sets and these in time-correct frame order. A moving boundary is something quite significant, but these should possibly not exclusively inspected through a hole ('convolutinal')
[ Parent
| on HN ]
Re:ImageNet-trained CNNs are biased towards texture (2019)
by rayuela on Monday April 20, 2020 @10:58AM
(#22924363)
Oh wow you're absolutely right. This is actually a really clever solution to the problem presented in this paper.
Re:ImageNet-trained CNNs are biased towards texture (2019)
by mbeex on Monday April 20, 2020 @04:21AM
(#22922118)
Oh, forgot an 'o'.