How to pronounce“imagenet”in English

I think ImageNet has been extremely valuable.

So I think ImageNet was useful, but basically, it's become a bit of an EMNIST at this point.

We've basically crushed ImageNet and there's no next-big benchmark that the entire community rallies behind and uses

deep learning hit imagenet that was a that was a shake

like this is what imagenet did exactly like it's not just there's always images the point is you aggregate them together

trained on imagenet trying to say what does this neuron do what do this does this family of neurons do what you can see is that

of work on looking at mnist and imagenet without training so it's like taking like the basic challenge is

back to the history of imagenet neural networks have been around for many decades as you mentioned what do you think were the key ideas

one phrase but but this is like imagenet but for every data task that's already

Like you're just starting with like something trained on imagenet, which is like Images of dogs and cats and things like that.

oh i think i think their performance their performance on imagenet was shocking the computer vision those early days was just very like wow okay

learning Revolution had just begun their systems like imagenet had suddenly been won by deep learning techniques back in 2012 and following that it was natural

and there was this competition called Don Bench of who can train ImageNet fastest, right?

steep and i talk with excitement about each of these entries of course the imagenet moment itself or the alexnet moment that launched a deep

and have recently had some words of criticism that the academic research ML community gives a little too much love still to the ImageNet

- Unfortunately, I don't think academics currently have the next ImageNet.

I mean that, yeah, why did ImageNet takeoff?

capture why attack the capture problem which is quite unique in the computer vision context versus like the traditional benchmarks of imagenet

think about the steps that are necessary to get there and hopefully that thing is not a better number on imagenet classification it's like it's probably

and big datasets, by the way, also Stanford, ImageNet, to sort of come together and, and create this sort of extraordinary explosion that's gonna shape the future.

You've criticized, you flourished, and loved for time the ImageNet, the famed ImageNet dataset

- Actually, I don't know that I recall the specific instance where I was unhappy or criticizing ImageNet.

- I think the way I've heard you just somewhere, maybe I'm just imagining things, but I think you said like ImageNet was a huge contribution

to the community for a long time and now it's time to move past those kinds of- - Well, ImageNet has been crushed.

you already a lot deeper understanding of what's happening and i think that that's where we're going very soon i mean we've we've had imagenet for a long time