Furthermore, those better results have the advantage of a much simpler model. This model has a fairly complicated architecture (a complex residual concatenation setup) and many more parameters (I would guess anywhere between 2x-10x as many, but I'd have to take a closer look), which means it's much slower to run and takes up more memory (disk and RAM).
I'd also say that in general the better model does things that are a lot more common sense: using the CIE Lab color space (perceptually uniform), omitting pooling, using a classification loss instead of regression (regression in generally performs poorly in deep learning), etc.
Furthermore, those better results have the advantage of a much simpler model. This model has a fairly complicated architecture (a complex residual concatenation setup) and many more parameters (I would guess anywhere between 2x-10x as many, but I'd have to take a closer look), which means it's much slower to run and takes up more memory (disk and RAM).
I'd also say that in general the better model does things that are a lot more common sense: using the CIE Lab color space (perceptually uniform), omitting pooling, using a classification loss instead of regression (regression in generally performs poorly in deep learning), etc.