MIT 6.S191: Taming Dataset Bias via Domain Adaptation

MIT Introduction to Deep Learning 6.S191: Lecture 10
Taming Dataset Bias via Domain Adaptation
Lecturer: Prof. Kate Saenko, MIT-IBM Watson AI Lab
January 2021
For all lectures, slides, and lab materials: introtodeeplearning.com​​
Lecture Outline
0:00​​ - Introduction
3:20 - When does dataset bias occur?
7:00 - Implications in the real-world
12:41 - Dealing with data bias
14:38 - Adversarial domain alignment
20:30 - Pixel space alignment
26:03 - Few-shot pixel alignment
33:56 - Moving beyond alignment
38:59 - Enforcing consistency
42:05 - Summary and conclusion
Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

[@saliexplore3094]

What a quality presentation. I love how she delivers an story line, declaring key assumptions and describing the approach for overcoming limitations of existing works.

[@gayathrianand3760]

The best introduction to domain adaptation

[@davicarvalho2536]

really insightful class! thank you very much for sharing!!

[@sandeepbansal9555]

awesome explanation :)

[@voquangtuong7389]

Thank you for oranigization and giving us a wonderful course. Can we get a slice lecture as previous. We are appreciate if we can a reference slice. Thank you again

[@hungnguyenmanh6168]

Thank you!

[@mihikataneja145]

Thanks for video and very good explanation. Could you please tell me how Divergence based Domain is different from Adaptation Divergence based Domain Adaptation?

[@MorisonMs]

Thank you Kate!
Does these methods works well for regression problems?

[@gauravprasad6266]

Yes, but you have to look for mathematical justification from Mehryar Mohri work on domain adaptation for regression

[@MorisonMs]

@@gauravprasad6266 Thanks for the comment

[@sarmadf.ismael2155]

Can I get the slides of the video? if it is available, I didn't find it on the attachment website

[@sarmadf.ismael2155]

?????? no response !!!

[@inspiredbynature8970]

i also want them

[@koushikdurgapu8649]

what is the use of a discriminator anyway we are going to fool the discriminator ?? what happens when we didn't use the discriminator?

[@amir4207]

👍❤

[@benxneo]

🇲🇾