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

131–140 of 235 posts

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

#131

Post by rsp1984 »

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.

In the examples they show an image of a woman next to a table. The table is covered with a table cloth. In the corrupted image the table cloth looks like all noise to the human eye, however in the reconstructed image you see that the method is able to recover most of the pattern in the cloth.

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

#132

Post by ben_w »

mjburgess wrote: post #130
sanxiyn wrote: post #125

Earlier quoted context omitted.

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 te…

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

The words “intelligent” and “conscious” are not sufficiently well defined to make that claim. By “intelligence”, do you mean:

1) “the ability to learn or understand or deal with new or trying situations”? Even current AI can do that.

2) “the ability to apply knowledge to manipulate one’s environment”? That’s another rabbit hole itself.

3) “think abstractly as measured by [tests]”? I think current AI fails at this.

4) the thing which is separate to “body” in Cartesian Dualism? I don’t believe in that (i.e. souls) any more, so I can’t claim any AI would pass this test (nor any human).

And “conscious”? Is that:

1) Opposite of unconscious? I’d say they are.

2) Opposite of subconscious? ‍️

2)a) As in, not just autonomous functions like breathing or the equivalent for a robot? I’d say they are.

2)b) As in, “System 2 thinking”? ‍️I don’t know.

3) Critical self-evaluation? Generative adversarial networks pass, other than that I think AI fail this test.

4) Mirror test? Pass, but in a special case I don’t know the details of and which might well be newspaper fluff rather than proper AI.

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

#133

Post by cdancette »

jpster wrote: post #102
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…

Does this mean huge datasets are no longer a prerequisite for this type of computing? Leveling the playing field for smaller teams who may no longer have to rely on Google- or FB-sized datasets?

I don't think so. They are basically loosing entropy by going from the corrupted image to the original one that's more predictable.

I don't think you can do other things like labeling by using the same method

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

#134

Post by amelius »

rsp1984 wrote: post #131
amelius wrote: post #122

Earlier quoted context omitted.

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.

In the examples they show an image of a woman next to a table. The table is covered with a table cloth. In the corrupted image the table cloth looks like all noise to the human eye, however in the reconstructed image you see that the method is able to recover most of the pattern in the cloth.

That's something different: a demonstration of an "inpainting" problem. The black pixels were specifically marked as corrupt. Also, the pattern on the cloth is much less granular than noise.

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

#135

Post by mjburgess »

ben_w wrote: post #132
mjburgess wrote: post #130

Earlier quoted context omitted.

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 te…

> Line up all the things in the universe that are intelligent. They are all conscious. The words “intelligent” and “conscious” are not sufficiently well defined to make that claim. By “intelligence”, do you mean: 1) “the ability to learn or understand or deal with new or trying situations”? Even current AI can do that. 2) “the ability to apply knowledge to manipulate one’s environment”? That’s another rabbit hole its…

> Even current AI can do that.

No it can't. A machine'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.

"The opposite of consciousness" is not a meaningful criterion of interest. I'm not even sure it's a meaningful term. It seems to commit the buddhist fallacy that causal processes at work in the universe are differentiated into opposites. That whatever causes rocks to fall must be the opposite of the thing that causes fire to rise. It isnt -- there isnt really anyway to define "opposite" with respect to what causes what.

Many of these tests you're outlining arent relevant to the question "does this robot have what we are interested in". Ie., is this piece of lead actually gold. Not "is it shiny with a brass coating" -- but can it participate in all the causal interactions gold can. I'm not concerned with how good the tool is, or how close we are to fooling people, i'm concerned with whether the robot can think.

Does the robot posses any concept? Any idea? Any understanding?

No, only metaphorically. It seems as-if it does to people who use it to aid in their understanding. It is only a trick, no more than an ancient human being being scared of a spinning top and wondering how it is so well able to navigate around the grain of the wood -- better than any beetle!

Intelligence as it is possessed by the relevant subset of animals which we're targeting possess concepts. They are biochemically connected to their environment. The understand it. The dog's finding its bone is NOT the same as the spinning top find its grove. Only by an extremely confused metaphor.

The dog puts to use thoughts, concepts, ideas, imagination (and many other things besides) that are about its environment. That it has acquired in its direct understanding of its environment. The spinning top merely topples towards its final point as-if it understood.

Machines are rivers of electrical current that topple toward and outcome that it sensitive to their current state, like a top spinning about a board. They have no active, navigating, biochemical motivated concernful goal-directed action.

My view is that they never will, since on all the best evidence, skillful concernful action is a neuro-bio-chemical process.

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

#136

Post by cdancette »

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.

You're right, and here, they're including the prior R(x) in the model architecture. So R(x) = 0 here,

and they pose x = f_theta(z), where f_theta is a neural net.

So they can avoid overfitting by stopping the training at the right moment.

So they're not really trying to minimize E(x, x0), but rather to get a small enough value, so that they obtain good results. A too small value means overfitting.

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

#137

Post by eitland »

cztomsik wrote: post #112
vbuwivbiu wrote: post #48

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

Thx for that!

Upvoted you both. I normally really don't like videos but this was worth the few minutes it took. (The link points to the middle of a 9 min video.)

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

#138

Post by rullelito »

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…

Can someone explain this in a way so that an ordinary mortal computer scientist can understand it?

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

#139

Post by LoSboccacc »

amelius wrote: post #134
rsp1984 wrote: post #131

Earlier quoted context omitted.

In the examples they show an image of a woman next to a table. The table is covered with a table cloth. In the corrupted image the table cloth looks like all noise to the human eye, however in the reconstructed image you see that the method is able to recover most of the pattern in the cloth.

That's something different: a demonstration of an "inpainting" problem. The black pixels were specifically marked as corrupt. Also, the pattern on the cloth is much less granular than noise.

still the problem space is greatly reduced - all we need now is a nn to detect corrupted pixels

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

#140

Post by mcny »

felippee wrote: post #44
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…

This is great work. It shows that some of the "amazing" results of deep learning are not as deep and don't even require learning! In my view this also sheds some light on the GAN's and their ability to generate "real looking images". Perhaps there is much less to generating "real looking images" then everyone attributes. E.g. in this work, the network clearly knows exactly nothing about the world and generates good l…

The results are amazing, at least to me!
Post reply on HN