Re:ImageNet-trained CNNs are biased towards texture (2019)
by stared on Monday April 20, 2020 @05:08AM
(#22922297)
They are, and it is not that new; the interesting part is how to solve that.
For image classification, this bias for textures may be passable. For image generation, it would produce atrocious results, especially for faces. To the point, that people devised some methods to overcome this, especially with progressive networks (e.g. proGAN). See https://towardsdatascience.com/progan-how-nvidia-generated-i... for the proGAN explanation - it starts from training on 4x4 pixel images, to get the overall shape.
For image classification, this bias for textures may be passable. For image generation, it would produce atrocious results, especially for faces. To the point, that people devised some methods to overcome this, especially with progressive networks (e.g. proGAN). See https://towardsdatascience.com/progan-how-nvidia-generated-i... for the proGAN explanation - it starts from training on 4x4 pixel images, to get the overall shape.