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

[@MrSupermonkeyman34]

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!

[@PD-vt9fe]

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

[@srh80]

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

[@_chappie_]

Even a toddler can understand this. Thank you.

[@loading_700]

Best lecture about Few-shot learning! Thank you

[@vibhasnaik1234]

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

[@semacandemir9629]

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

[@rm1768]

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

[@user-wr4yl7tx3w]

Best explanation of Meta Learnings

[@yonghengwang7511]

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

[@_ifly]

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

[@karanacharya18]

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

[@zoelav1398]

Extremely clear explanation. Thank you so much.

[@SpenceMan01]

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

[@nlptranslationgroup2]

Wonderful explaination

[@AiDrug]

Thank you so much! Great explanation

[@emanali1197]

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

[@x-Factor461]

Thank you for this video. It's awesome

[@anirudhthatipelli8765]

Thanks for such a detailed explanation!

[@sunxiyana2442]

The best explanation ever

[@__-pd7tc]

በጥሩ ሁኔታ አብራርተህልናል፣ በጣም እናመሰግናለን

[@souraya19]

Thank you so much for this amazing explanation

[@北海苑优质男]

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

[@nannuakand8076]

Awesome!!! A Great presentation, Thank you!

[@liminm]

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

[@ShusenWangEng]

Thanks. Just uploaded the 2nd part. Will upload the 3rd in a day.

[@mmazher5826]

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

[@benjaminbenjamin8834]

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

[@hossein3908]

Thanks a million. extremely good explanation and brilliant slides.

[@mohammedal-qudah9518]

Thank you.
I like the explanation

[@akhilkishore8240]

Thanks for the clear explanation

[@zahraghorbanali98]

such a good explanation, Thanks!

[@basiljacob3894]

Wonderful explanation . Thankyou sir for this amazing content

[@chantata]

thank you for your explanation..!

[@이정민영어]

이해가 잘됩니다. 감사합니다.

[@somerset006]

Really good explanation, thank you!

[@عائشةالرميح-ز8ز]

Many thanks

[@airesearch8057]

Thank you so much.

[@cw9249]

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?

[@syedmustahsan4888]

Thank you very much
Pretty good way of teaaching

[@nidcxl4223]

Great presentation. Thank you professor Wang

[@aidynabirov7728]

Thanks a lot!

[@nidcxl4223]

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.

[@ShusenWangEng]

It depends on how they are computed. If they are the outputs of Softmax, then they add up to 1. If they are computed by the Siamese network, then they don't.

[@hossein3908]

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

[@alphonseinbaraj7602]

Really awesome sir..

[@sydneystriker5355]

Nice Work. Thanks

[@tipycalflow1767]

The animal in the water is an otter
Nice rhyme

[@talha_anwar]

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

[@ShusenWangEng]

No, the classes of support set do not appear in the training set (e.g., Imagenet).

[@moetezsoltani2182]

What about zero-shot learning

[@anishhui192]

Thank you!

[@francycharuto]

Amazing

[@wilsondq0c]

Thank you!,

[@yarasultan3433]

nice

[@Hshjshshjsj72727]

Its 2024 please stop using a potato as a microphone

[@diamond2869]

Thank you!