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

171–180 of 235 posts

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

#171

Post by ska »

vbuwivbiu wrote: post #48

Remember fractal image compression ? https://youtu.be/AjdogjBxfco?t=260

This can also be looked at as the original source of patch based denoising, etc. In the end it's about capturing the scaling properties and self similarity of natural images. This is also, for example, why wavelets were so effective as a basis.

David Mumford particularly did some great work on this sort of thing a couple of decades ago, along with many others. I hope when people are rushing around trying to apply convolutional nets to everything they aren't losing these insights.

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

#172

Post by ska »

eref wrote: post #104
andbberger wrote: post #101

Earlier quoted context omitted.

One more relevant note - (Olshausen and Field, 1997) showed that the filter employed by V1 simple cells could be learned using some simple assumptions about sparse coding and a single image. Translation invariance built in by way of the sampling scheme of the image, small patches. The filters learned by the first layer of CNNs is usually of the same type, Gabor filters. Not a coincidence. That was twenty years ago. W…

What do Gabor filters have to do with this?

Parent is saying Gabor filters are typically effectively recapitulated by the first layer of of the network anyway, as they are a natural representation.

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

#173

Post by ConfucianNardin »

mjburgess wrote: post #155
ConfucianNardin wrote: post #143

Earlier quoted context omitted.

> Even current ("real") intelligence can do that. No it can't. A biological creature's output is not deterministic from its input and can be sensitive to conditions not anticipated at-programming-time. That isn't understanding. A spinning top may spin on many surfaces not anticipated by the designer and acquire all sorts of interesting behaviors by doing so. [...] Many of these tests you're outlining aren't relevant…

What you've done here is expose an epistemological problem but not the ontological one under consideration. My ontological premises are: consciousness exists and it is a neurochemical process. From this follows: machines which are not instances of this process are not conscious. Now you have basically said: but we do not know for certain that it is this neurobiochemical process that accounts for consciousness. Isnt i…

No, the issue is with the very premise, then.

It is not clear that consciousness necessarily only emerges from a neurochemical process.

What was basically said was "We do not know for certain that it is this neurochemical process that accounts for consciousness. Isn't it reasonable to suppose that we might encounter things that actually are conscious, but whose consciousness is not accounted for by the same property (neruochemical) of the underlying process."

I'm not sure that stated premise is very useful, since it borders on the tautological.

The dog (or even a human doing some task) is akin to an intricate state machine whose next state depends on the current state and its environment. Just like the spinning top. For each of those we modify the lower level mechanisms to effect a different high level behavior. Changing the thing in the former case (Cocaine/neurosurgery) or its environment (steal the bone). Changing the thing in the latter case (cutting out part of the spinning-top) or its environment (carving the surface it spins on).

The difference in the two cases being the number of intermediate steps (or abstraction layers if you will) between the high level behavior and the low level mechanisms from which it emerges, and the complexity of the emergent behvaior.

Illusion: the low level mechanisms (biochemical or otherwise) that, using the current state and the environment, transition to the next state, and in the process "present" an experience that we interpret as ourselves thinking, making decisions, taking skillful actions and so on.

If we observe the target phenomenon "skillful action" we discover that all known occurrences are biological. This doesn't really preclude the possibility of other mechanisms producing it.

To modify the behavior of a machine, you cannot use cocaine. That's because the machine has no receptors for the comprising molecules - not because it has no thoughts. You could instead modify the logic gates it possesses instead by applying a certain pattern of electromagnetic radiation which would cause interference, just like the cocaine interferes with the normal workings of the brain.

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

#174

Post by ac2u »

wonderous wrote: post #86
ac2u wrote: post #84

Question to anyone that knows this area in depth. I'm assuming that this impressive feat has a disadvantage (over the traditional example intensive technique of training a CNN with something like ImageNet) in the form of taking a long time to generate the corrected image. With that assumption in mind, could this new technique be reversed? As in feeding in sharp images, getting back out corrupted ones, for the purpose…

Do you mean generative adversarial networks? https://en.m.wikipedia.org/wiki/Generative_adversarial_netwo...

No not really, this isn't generation for the sake of classification. It's generation in order to generate a dataset to train a new network that exhibits the characteristics of the network in the paper that can be used quickly and in a more general fashion.

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

#175

Post by mjburgess »

ConfucianNardin wrote: post #173
mjburgess wrote: post #155

Earlier quoted context omitted.

What you've done here is expose an epistemological problem but not the ontological one under consideration. My ontological premises are: consciousness exists and it is a neurochemical process. From this follows: machines which are not instances of this process are not conscious. Now you have basically said: but we do not know for certain that it is this neurobiochemical process that accounts for consciousness. Isnt i…

No, the issue is with the very premise, then. It is not clear that consciousness necessarily only emerges from a neurochemical process. What was basically said was "We do not know for certain that it is this neurochemical process that accounts for consciousness. Isn't it reasonable to suppose that we might encounter things that actually are conscious, but whose consciousness is not accounted for by the same property…

Scientific claims are not necessities. I'm not saying I can prove consciousness is a biological process only that its overwhelming reasonable to suppose so.

Emergence is a result of causal interactions between parts of a system being different than the internal causal interaction within one part. It doesnt mean "complexity" and it really has nothing to do with a machine.

The oscillating electric field acquires no new causal interactions as the program complexity increases. Adding more H20 to a single H20 creates new causal interactions (eg. wetness).

> That's because the machine has no receptors for the comprising molecules - not because it has no thoughts

Right, so you're supposing a contrary entirely bizarre ontological view: that thoughts are something independent of a biological process.

Of all the known things in the universe which think, to remove their nerves is to destroy their capacity to think. I cannot see any reason to suppose thinking is not merely their activity.

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

#176

Post by LoSboccacc »

asfdsfggtfd wrote: post #147
amelius wrote: post #141

Earlier quoted context omitted.

We need more than just the information where corrupted pixels are. For example, consider an image of a woman, severly blurred such that her individual fingers cannot be discerned but you can still see that it's a woman. A "learned" context-aware approach can now deduce that the "blob" that is her hand should be inpainted by fingers. A non-learned approach can't do that.

But the fingers it draws will be random fingers. Not her fingers.

true but it's still pretty amazing that those specific number fluctuations represent fingers (random or otherwise) without training

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

#177

Post by bitL »

scotty79 wrote: post #93
cs702 wrote: post #23

Earlier quoted context omitted.

I'm wondering the same thing too. Note also that this finding strongly suggests that neural net architecture actually is quite important, possibly even more important than having more data -- which contradicts the conventional wisdom!

It's not about neural network architecture. CNNs are taught by presenting them overlapping pieces of image. To speed things up and keep things orgsnized this is not done sequentially but in parralel making multiple neurons share weights but this is just a trick. So what makes this result possible is not the architecture of NN in CNN but rather architecture of C. That allows us to get multiple samples from single imag…

I think it's both C and NN. Don't forget each new C layer groups information from previous layers; using just a single C layer won't do you much good. It might not reflect brain much but it kinda resembles what retina/visual cortex neurons do; CNNs were actually inspired by visual field maps found in visual cortex and somebody had the idea that C is the most similar CV operation we have, and put them together. To everyone's surprise it worked nicely.

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

#178

Post by fenwick67 »

killjoywashere wrote: post #53

The intel and espionage communities are going to be all over this. This makes the Soviet photo retouching look like child's play. Let's say you want to start a war, and need some evidence of chemical weapons. Now, you can drop in some images of chemical weapons and claim a GAN found them. Sample press releases: "We believe this photo was retouched to hide the chemical weapons. Using a GAN, we recovered clear photogra…

I'll grant you that it makes a good scapegoat, but frankly this doesn't really matter... the US went to war with Iraq with bad intel before the machine learning boom.

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

#179

Post by CardenB »

Mahn wrote: post #162
flyingspork wrote: post #33

Earlier quoted context omitted.

Not an expert so take this with a grain of salt; I could be misinterpreting the paper. It seems that the current accepted method is to train a network with distorted images as the input and the correct undistorted images as the targets. Then after training you can feed a new distorted image into the trained network and get the estimated "fixed" image. However this team actually uses the distorted image as both the in…

> for some reason, the structure of the network means that the estimated output learns realistic features first, and then overfits to the noise afterwords. Why does this happen? What characteristics does the network structure have that cause this effect?

I think the reason this paper is so interesting is that no one had any idea why this happens

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

#180

Post by wonderous »

ac2u wrote: post #174
wonderous wrote: post #86

Earlier quoted context omitted.

Do you mean generative adversarial networks? https://en.m.wikipedia.org/wiki/Generative_adversarial_netwo...

No not really, this isn't generation for the sake of classification. It's generation in order to generate a dataset to train a new network that exhibits the characteristics of the network in the paper that can be used quickly and in a more general fashion.

Meaning that your assumption is that there is an optimal generalized network structure for generate a neural network as described in the paper and that as such, what is missing from the research is how to create an optimal way to generate a malformed source/target seed.

Is that correct?

Post reply on HN