Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Deep image prior 'learns' on just one image

dmitryulyanov.github.io

Post reply on HN
Print view View original

121–130 of 235 posts

Re: Deep image prior 'learns' on just one image

#121

Post by sigterm »

blauditore wrote: post #113

As I'm not an expert in the field; what exactly does the term min_x E(x; x0) + R(x) mean? I thought that E(x; x0) would denote the error/difference between original and corrupted images, and R(x) be the (searched-for) correction. But this doesn't seem to make sense with the next parts of their explanation.

I think x_0 refers to the corrupted image and x is the (denoised/upscaled/inpainted) image the optimization algorithm tries to come up. Without R(x) the optimal solution is simply x=x0. So we need a good R(x) that can measure how good or natural the solution image is. In this work the R(x) is constraining the valid x to those that can be represented by a CNN.

Re: Deep image prior 'learns' on just one image

#122

Post by amelius »

cs702 wrote: post #21

Wow: "In this work, we show that, contrary to expectations, a great deal of image statistics are captured by the structure of a convolutional image generator rather than by any learned capability. This is particularly true for the statistics required to solve various image restoration problems, where the image prior is required to integrate information lost in the degradation processes. To show this, we apply untrain…

But I see one problem. Say the image is a photo of a driveway. The gravel on the driveway will look like noise. Will the algorithm now smooth out the driveway, effectively removing the gravel?

At least a "learned", context-aware approach can prevent this from happening in theory.

Re: Deep image prior 'learns' on just one image

#123

Post by cygaril »

gfcft wrote: post #111
eanzenberg wrote: post #98

Earlier quoted context omitted.

Seems like this view gets told every once in a while by someone who clearly hasn't been around any 0-2 year olds.

This is HN, what did you expect? Real people with wife and kids?

Women are real people too.

Re: Deep image prior 'learns' on just one image

#124

Post by urgoroger »

JumpCrisscross wrote: post #24

Can someone break this down for this layman?

Could be wrong too, ML is not my field.

Basically, a generator neural network has two things which affect its output: an input and some parameters (weights).

Let's use the setting of the task for denoising images. They use a network who's output is to is the denoised image, and compare it to the noisy image to get a score for how good the denoised output was.

Now the strange thing is, for the input of the network, they just use random garbage. The only thing they move around to try get a good denoising score are the parameters of the network (not the input).

They find that by only adjusting the parameters, even with fixed random crap inputs, if they find the parameter setting which minimizes the noise, they actually still get great looking results.

This suggests that the networks they tested this method with (other researchers work who do well on this task) are based much more in the inherent structure of the network, rather than the model refinement from training on thousands of images, since even given random crap, they generates good results, as long as the parameters are tuned well to the noisy image.

Re: Deep image prior 'learns' on just one image

#125

Post by sanxiyn »

mjburgess wrote: post #119
cs702 wrote: post #32

Earlier quoted context omitted.

Thanks. I'm not mixing them up! I'm just wondering whether and to what degree architecture , i.e., network structure, will prove important for other, more advanced AI tasks, including up to AGI.

To throw a dissenting voice into the mix: I do not think intelligence is a consequence of structure. Transparency is a consequence of how light interacts with objects. There is no "transparent gold". And being transparent is not something we can program gold to do. Programming is the application of an electric field across a silicon surface: this can no more transmute silicon into gold as it can into a nervous system…

Who said anything about consciousness? Intelligence does not equal consciousness.

Re: Deep image prior 'learns' on just one image

#127

Post by zgao »

cs702 wrote: post #32
jmmcd wrote: post #30

Earlier quoted context omitted.

> PS. This makes me wonder whether and to what degree the structure of the brain's connectome is a necessary prior for AGI. Well, I wouldn't mix up AGI and AGI by deep learning, and more important I would emphasise that this is a good prior for images . The fundamental insight in CNNs and eventually in this work is that there is a correlation between pairs of nearby pixels. We have something similar for video and aud…

Thanks. I'm not mixing them up! I'm just wondering whether and to what degree architecture , i.e., network structure, will prove important for other, more advanced AI tasks, including up to AGI.

Although probably not sufficient for AGI, network architecture is essentially guaranteed to be important, because of both ample empirical evidence of the importance of architectures and ample reason, from facts about numerics, to believe that it is important.

In the first category (empirical evidence),

- The discrete leap from non-LSTM RNN to LSTM network performance on NLP was essentially due to a "better factoring of the problem": breaking out the primitive operations that equate to an RNN having "memory" had a substantial effect on how well it "remembered."

- The leap in NMT from LSTM seq2seq to attention-based methods (the Transformer by Google) is another example. Long-distance correlations made yet another leap because they are simply modeled more directly by the architecture than in the LSTM.

- The relation network by DeepMind is another excellent example of a drop-in, "pure" architectural intuition-motivated replacement that increased accuracy from the 66% range to the 90% range on various tasks. Again, this was through directly modeling and weight-tying relation vectors through the architecture of the network.

- The capsule network for image recognition is yet another example. By shifting the focus of the architecture from arbitrarily guaranteeing only positional invariance to guaranteeing other sorts, the network was able to do much better at overlapping MNIST. Again, a better factoring of the problem.

These developments all illustrate that picking the architecture and the numerical guarantees baked into the "factoring" of the architecture (for example, weight tying, orthogonality, invariance, etc.) can have and has had a profound effect on performance. There is no reason to believe this trend won't continue.

In fact, there are some very interesting ways to think about the principles behind network structure -- I can't say for sure that it has any predictive power yet, but types are one intuitively appealing way to look at it: http://colah.github.io/posts/2015-09-NN-Types-FP/

Re: Deep image prior 'learns' on just one image

#128

Post by pasta »

amelius wrote: post #122
cs702 wrote: post #21

Wow: "In this work, we show that, contrary to expectations, a great deal of image statistics are captured by the structure of a convolutional image generator rather than by any learned capability. This is particularly true for the statistics required to solve various image restoration problems, where the image prior is required to integrate information lost in the degradation processes. To show this, we apply untrain…

But I see one problem. Say the image is a photo of a driveway. The gravel on the driveway will look like noise. Will the algorithm now smooth out the driveway, effectively removing the gravel? At least a "learned", context-aware approach can prevent this from happening in theory.

I think you are right.

But as a brush in a photo editor program it would be great. Then a used can 'mark' what areas need to be smoothed and the result will be great.

Re: Deep image prior 'learns' on just one image

#129

Post by warsheep »

fpgaminer wrote: post #107

I'm finding it hard to put into words what I find wrong with this paper, but ... here goes nothing. So, the novel thing here is that an encoder-decoder network applied to an image can learn enough from a source image to be useful. In some ways that's obvious, but the effectiveness of it on reconstruction tasks is certainly surprising. I have two problems, though. One is that I would take the reconstruction results wi…

> Convolutional layers are just simplifications which make training easier. They are priors in the sense that we know a fully connected layer in image applications would just devolve into a convolutional layer anyway, so we might as well start with a convolution layer. That "design" is the prior. But it's not mandatory; the network would still function without that "prior".

As far as I know this is incorrect. Can you point to a paper that shows this? If by "easier to train" you mean that the models do not overfit training data, then that's the whole point of using correct priors / hypothesis classes.

I'm not sure what bugs you in this paper, but the point is that they decouple the prior architecture from the training/optimization mechanism, and that seems interesting.

Re: Deep image prior 'learns' on just one image

#130

Post by mjburgess »

sanxiyn wrote: post #125
mjburgess wrote: post #119

Earlier quoted context omitted.

To throw a dissenting voice into the mix: I do not think intelligence is a consequence of structure. Transparency is a consequence of how light interacts with objects. There is no "transparent gold". And being transparent is not something we can program gold to do. Programming is the application of an electric field across a silicon surface: this can no more transmute silicon into gold as it can into a nervous system…

Who said anything about consciousness? Intelligence does not equal consciousness.

Line up all the things in the universe that are intelligent. They are all conscious.

Unless you mean "imitating intelligence", but that's not what AGI (artificial general intelligence) is targeting.

An AGI robot would be one to include in any future line-up of "all the things that are intelligent". My view is that unless an AGI robot has a nervous system, it will never belong in that category.

It is fashionable in tech today to speak metaphorically with abandon and to call whatever we like "intelligent" (and to have, machine "learning", etc.). These systems are no more intelligent than an abacus: upon inventing a wood-to-lcd converter, we could run Win95 on a few million wooden beads.

Metaphorically, these are intelligent. They fill the role of prior uses of genuine intelligence -- ie., they can help us calculate and therefore substitute our calculative conscious behaviours for non-conscious substitutes. They are tools.

My hammar is no more intelligent than my laptop however. Neither possess thoughts, nor can conceptualize or understand anything. A concept is a (biochemical) technique an animal acquires through a biochemical interaction with the world: an electric field can not have concepts.

The argument that machines-which-seem-intelligent are intelligent is only a fallacy of ambiguity. What we mean, of machines, is a tool-which-helps-conceptualizing. We we mean of general intelligence is conceptualizing. The former and the latter are not the same. In a universe only of tools, nothing thinks to use them.

Post reply on HN