Few-Shot Learning (1/3): Basic Concepts 

Have literally spent the last couple of days trying to understand few shot learning for a university project and haven't been understanding it at all until this video. Great explanation, thank you so much!

Best lecture about Few-shot learning! Thank you

Thanks. One of the few videos that explained this concept with near zero jargon.

Wonderful. The best explanation on Few-shot I've seen so far. Thank you!

Thank you! the presentation helped me to understand few-show learning.

Even a toddler can understand this. Thank you.

በጥሩ ሁኔታ አብራርተህልናል፣ በጣም እናመሰግናለን

Man it's difficult to tell between a beaver and an otter

You save my time to learn this concept. Thank You!

Best explanation of Meta Learnings

Best video on this concept! Please keep up the great work! Thank you!

Thanks for making it look like a piece of cake. I look forward to many more lectures from you.

Extremely clear explanation. Thank you so much.

Brilliant, intuitive explanation of few-shot learning! Thank you for uploading.

Thank you for this video. It's awesome

王老师，我从您这里学到了很多东西，非常感谢您，希望您以后能发布更多的学习视频

Thank you so much! Great explanation

Thanks for such a detailed explanation!

이해가 잘됩니다. 감사합니다.

Thanks for the best explanation ever. I really appreciate your effort.

Thank you so much for this amazing explanation

Hello, I found this video helpful. Could you maybe also upload the other parts? Thank you.

Many thanks

your lectures are very easy to understand. Keep it up👍

Thank you. I like the explanation

Thank you!

The best explanation ever

Awesome!!! A Great presentation, Thank you!

thank you for your explanation..!

Thanks for the clear explanation

such a good explanation, Thanks!

Thank you so much . That was extremely good explanation , please carry on .

Thank you so much.

12:51 Just had to say that your support set image of the two hamsters aren’t hamsters. Those are guinea pigs.

Really good explanation, thank you!

does this mean if you train the model using a particular support set, then in testing, if you add a new classes to the support set (never seen before), the model would still be able to find that a query belongs to the new class even though it was never trained using that new class in the support set?

Thanks a million. extremely good explanation and brilliant slides.

Wonderful explanation . Thankyou sir for this amazing content

Thanks a lot!

The animal in the water is an otter Nice rhyme

I think prepare a good support set is so challenging. is it true? What was the criterion for selecting these images (support set)?

Thank you very much Pretty good way of teaaching

Really awesome sir..

Nice Work. Thanks

nice

Why don't the similarities add up to 1? Aren't the classes mutually exclusive? Or is it not about the classes being mutually exclusive, but the fact the sample and the input overlap like a drawing and its reference. So that the an input image can be like other images even if that's not the correct class.

Is it necessary that classes of support set should be in large data such imagenet data?

Great presentation. Thank you professor Wang

Amazing

Thank you!,

What about zero-shot learning

Its 2024 please stop using a potato as a microphone

Thank you!