Human vs AI Vision
The cluster discusses comparisons between human and AI (neural net) capabilities in image recognition, particularly in tricky scenarios like optical illusions, adversarial examples, and camouflaged objects, debating limitations in abstraction, context, and generalization.
Activity Over Time
Top Contributors
Keywords
Sample Comments
Not quite the same, show humans one picture of a giraffe and most humans will recognise the animal in different conditions, poses, angles and so on. Any neural net (up till now) has a difficult time doing the same.
I was pondering on this topic earlier today and came to the conclusion, "because our performance is judged only by humans." Imagine if an alien visited Earth, and was completely dumbfounded by our sketches and cartoon drawings. "But it looks nothing like a chicken", they say, looking at a sketch of a chicken and a photo of a chicken. "It's just an edge case that happens to trigger your 'chicken' neuron."
What object in a picture can be detected just by a human but not a machine?
Neural net can see some subtle pattern invisible to human eye, decide it is very representative, and make a guess based on that.Pre-processing seems to be an answer, normalize the image, blank out areas obviously uninteresting to human eye, add dithering.
It's not just the time. Computers don't have higher reasoning that can cross-check the results with expectations from a more complex world model. So by just flashing images I guess you only activate some earlier parts of the visual processing machinery. So that's quite fair to the computers since their NNs only do primitive pattern checking without reasoning too.
Humans are pattern recognizers... what did you expect?
its not the eye thats doing the recognition. The human brain is still more impressive than any machine
As the AI has likely not seen anything remotely similar during training, it is quite interesting that it is detecting the animals. As the picture was set up to confuse humans, does it somewhat show, that the representation that the AI learned is similar to the one humans have?
Not really, however it is interesting that how AI can see the picture. It is still a magic to me that it sees pixel different than us
Not entirely true. The model can extract image information from the pixels a human might not be able to see. Like how you can enhance the colors in a video of a face in a way that it pulses red with your heartbeat. The information about your heartbeat was there all along, our eyes were just not able to extract / recognize it.