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.
For comparability, I think it would be best if we could see outputs for the two models for the same, chosen in advance and not cherry picked, images.
What I imagine is full color input -> create B/W & color histogram (list of colors used) -> image viewer uses colorization algorithm to reapply colors.
I don't think a compression technique that would require that much processing power and have that little size reduction would be too useful.
Congrats, you wrote the first colorblind NN ever!
(Or you could just try to use a RNN directly and keep hidden state from frame to frame.)
The widely known Ben Hur (1959), the one with the chariot race, already is in colour. Did you mean "Ben-Hur: A Tale of the Christ" from 1925?
I'm interested to see if neural network parameters become the new "binary blob". While in theory you could always retrain the network yourself, actually doing so takes a lot of work fiddling with the network's hyperparameters and requires significant computing resources.
[1] http://www.robots.ox.ac.uk/~vgg/research/very_deep/
[2] "On a system equipped with four NVIDIA Titan Black GPUs, training a single net took 2–3 weeks depending on the architecture." - arXiv:1409.1556
Open source does not just mean you can see the source. From Wikipedia[0]:
"Open-source software is computer software with its source code made available with a license in which the copyright holder provides the rights to study, change, and distribute the software to anyone and for any purpose."
It's still interesting and cool to see! Just not what I thought it was when I clicked on the link.
In biometrics, there's been similar cases of software like face detectors and face recognition working very well on people from China and not very well for other people, because all the researchers who trained those models only had available large public databases from Chinese universities. The model hadn't seen any other ethnicity so its performance on "non-Chinese" folks wasn't surprising.
http://www.slashfilm.com/orangeblue-contrast-in-movie-poster...
I'd love to combine this technology with this: http://matplotlib.org/style_changes.html
You would probably have some cool results as you could generate examples of what they would look like to color blind people, and a corrected set so color blind people could see them.
Would be a cool, and I am assuming simpler problem then the one you have already managed to solve.
Good show, great work.
"But you didn't say what colour it was, so I made it a red truck."
Generally it's interesting to see nn thinking out missing details. I'd like to see images with an element deleted and a nn filling in black spots to see what level of shape recognition could do.
There is no way, from the greyscale, to know that the sky should be orange.
I've found this: [1], but the results seem somewhat disappointing. One of the problems is that the quality measures are (in my case) subjective (the results should look convincing but need not be "perfect", whatever that may mean).
[1] http://engineering.flipboard.com/2015/05/scaling-convnets/
