Seeing the Forest For the Trees 64
swframe writes "A new object recognition system developed at MIT and UCLA looks for rudimentary visual features shared by multiple examples of the same object. Then it looks for combinations of those features shared by multiple examples, and combinations of those combinations, and so on, until it has assembled a model of the object that resembles a line drawing. Popular Science has a summary of the research. I've been working on something similar and I think this accomplishment looks very promising."
This is a realization of David Marr's early work. (Score:5, Interesting)
Marr was a faculty member at MIT, so it is appropriate for this work to have been done there.
For more information, see:
http://en.wikipedia.org/wiki/David_Marr_(neuroscientist) [wikipedia.org]
and
http://www.amazon.com/Vision-Computational-Investigation-Representation-Information/dp/0716715678 [amazon.com]
-Todd
Re: (Score:3, Informative)
You know, two people or groups can arrive at the same conclusion, because it was obvious in the first place. And why is it so appropriate? What if the work had been done elsewhere, would that be inappropriate or offensive?
I should have been more specific in my first post.
David Marr's vision book (published in 1982 after his early death in 1980) is considered a seminal work in understanding human visual processing.
Marr was trying to describe how humans see. The new work at MIT is trying to allow computers to see. David Marr would be glad to see the developments, whether at MIT or elsewhere.
-Todd
Yes, but... (Score:2)
...will it sort my porn collection according to the models?
Re: (Score:1)
Wow - that's strange... (Score:4, Funny)
Maybe if enough of us with the same project interests get together, we can create an accurate summary of the parent!
You see? We could look at each other's projects for combinations of features shared by multiple examples, and combinations of those combinations, and so on!!??
This is amazing!
Re: (Score:2)
Re: (Score:2)
Well I am Patrick.
While you chaps theorise (Score:5, Interesting)
cool video! Re:While you chaps theorise (Score:2)
I was impressed the asimo guessed, "Maybe toy car?" when looking at the hand-sized mini-cooper model.
I did want to see them work on overlapping categories, like: is-a(toy) and is-a(car).
Re: (Score:2)
Well, they are teaching Asimo as if he/she/it were a small child, so the learning may take a while, and of course, honesty is important. I was impressed with the spacial analysis, given that it was much, much worse when I had machine vision. Processing was quite slow, IMO, but it is identifying general shapes like that of the toy car, which is good.
Ah, machine vision, where I had the most anal-retentive, closed minded professor ever. I don't regret not continuing with him for four more semesters and then
Re: (Score:2)
Yeah! Fuck the academics! What has research ever brought us, amirite?
Which Goal: AI or Cognitive Science? (Score:2, Informative)
A system can't just "learn" - does it use a GA? (Score:4, Interesting)
Even neural nets have to be programmed at some level to exhibit behaviour that the programmers think will allow them to learn the task at hand unless these guys used some sort of genetic algorithm. The article doesn't mention it. Does anyone know?
Also it doesn't explain whether the system just recognises similar pictures to what its seen before - eg this picture looks like object type 123 (which to a human would be a horses rump) or whether it can combine all views of an object and recognise them all as that object , eg this picture looks like a horse. If its the latter how does it do it - does it have to be shown the object from a large number of angles or can it just infer from a couple of angles what the object would be like from many others?
Re: (Score:1, Informative)
?There's nothing particularly unique about genetic algorithms with respect to learning? All systems operate within the constraints set by their programming.
Re: (Score:2)
The system is trained with labelled views of pre-categorized images, i.e., "this is one view of a watch, " "this is another view of a watch," etc. What makes it novel is that it is not told what the identifying features of a watch (or any other object are). It figures out for itself that the circular face, the stem, etc. are the distinctive features of a watch.
Re: (Score:2)
Some neural nets can learn on their own, without training. It shocked me too the first time I read of it.
Dammit, I can't find a reference now. The example I read about was classifying plants in broad and more specific types - the only input was data describing each of the plants.
Re: (Score:2)
Hey, that was my 8th grade science project!
Re: (Score:2)
Great, then you should know what the name is... ?
Re: (Score:3, Interesting)
No, because it doesn't.
Upper paleolithic european cave art used continuous, flowing lines [wikipedia.org], created by spit-painting (think prehistoric mouth airbrush), not short, overlapping, straight lines [mit.edu]. The system described in TFA produces results that resemble the sort of lame, pseudo-cubist drawing one saw in art schools in the mid 20th c.
dogs etc (Score:4, Interesting)
They just learn all the types (Score:4, Insightful)
Theres no way just from looking at pictures of dogs that you could tell they're all the same species. There are some characterstics that some breads have in common with others (other than the obvious 4 legs etc) but they don't all overlap. With something like this its more than a simple case of pattern recognition - its aquired knowledge.
Re: (Score:2)
Except pattern recognition *is* acquired knowledge.
Re: (Score:2)
No it isn't. If someone tells you "that is a dog" then you learn a simple fact without any patterns coming into it apart from being able to recognise what the particular breed of dog looks like in the future.
Re: (Score:2)
And of course you didn't watch the video. What they said is vision has a lot of background processing, whether you realize it or not (maybe it happens during REM sleep? I don't know). It is why we can identify the differences between, say, a dog and a badger or know a Terrier is a dog and a Pug is a dog despite body differences.
If you walk into a room you've never been in before, how many items can you identify given 5 seconds? 15? 30 trips into the room for 5 seconds? My guess is the more exposure,
Re: (Score:2)
Learning is multi-sense. We recognize dogs as much from the sounds they make and their behavior as from pure visual appearance.
Attempts to do reductionist recognition (i.e., one sense at a time) are doomed to mediocrity. This system doesn't even categorize it's own training set - it has to be fed labelled (i.e., pre-categorized) images.
Re: (Score:2)
There are some characterstics that some breads have in common with others (other than the obvious 4 legs etc) but they don't all overlap.
And this, my friends, is exactly why you should not use plutonium for baking.
Re: (Score:2)
Acquired versus earned knowledge could well be a huge factor in getting something like this to work.
Perhaps rather than using one A.I. system to recognize everything, what's needed are hundreds or thousands of specialized A.I. clusters, all working on specifically recognizing one particular kind of object by gathering as much property data as possible.
Then, hand that data down to the next tier of A.I. clusters charged with recognizing several kinds of similar objects using pattern recognition on the data fr
Re: (Score:2)
Well, you had strong behavioral tips there, how those two animals typically interact with each other. A bit reversed in many ways in comparison to female - male relations...
Re: (Score:2)
I'm not sure I've seen many cats until I was older (10 years maybe). We lived pretty secluded, only had a dog (and we only saw that dog maybe a couple of times a day or less). We had plenty of poultry though, and we played with chicks (we run after them mostly)
Re: (Score:2)
It probably largely relies also on observation of behavioral patterns, most dogs have pretty similar ones. And this is the time when child soaks in, at tremendous speed, the "rules" of social life.
Re: (Score:2)
I [...] have wondered how [...] young children recognize a dachshund, a bulldog and a great dane as dogs
It probably largely relies also on observation of behavioral patterns, most dogs have pretty similar ones.
Or, in layman's terms, dogs go "woof".
4 legged animals = "doggy" (Score:2)
Re: (Score:2)
It's also well known that children tend to have trouble with categorizing animals. Frequently they'll overgeneralize - calling every 4-legged animal a dog, for example - and it's only with constant correction that their category boundaries become adjusted properly.
Re: (Score:2)
For example, dogs bark and cat's meow.
Training (Score:2)
putting this into perspective (Score:3)
Hierarchical models of object recognition are decades old, as are attempts to implement them. This work doesn't yet work better than other engineering solutions, and it isn't obviously any more plausible than other approaches. So, it's a nice start, but it isn't a breakthrough.
Great (Score:2)
And here is the link to the paper itself (Score:4, Informative)
http://people.csail.mit.edu/leozhu/paper/RCM10cvpr.pdf [mit.edu]
The main achievement claimed is that no image labeling or any additional data like viewport position was needed, the learning process was completely automated.
Re: (Score:1, Flamebait)
...how long it takes before Big Brother decides he can use this to track all of the "troublemakers" in large crowds (everyone is a troublemaker, according to the Gov't).
Apparently the Flamebait mod is now given to people who disagree with the Party...
Re: (Score:1, Flamebait)
ah ha ha. ...or maybe just to those comments consisting of knowingly over-simplified-to-falsehood, generalizing, argument-inducing statements that don't contribute to the conversation and are about off-topic subjects, particularly "government"?
It's an extremely valid concern. If I disagree with the Gov't's actions, I can't exactly take my business elsewhere, can I? Sure, I can go find another one, but I can't go without one, or start my own (with the idea of doing it right). A private company can't fine me, put me in jail, nor can it execute me. The government can. That's why I usually direct concerns at governance about really great technology (it is really cool). But I don't want it turned against me. And if the government turns it against me,
What's an object, anyway? (Score:1)