MIT 6.S191: Taming Dataset Bias via Domain Adaptation
Вставка
- Опубліковано 14 чер 2024
- 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!! - Наука та технологія
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.
The best introduction to domain adaptation
really insightful class! thank you very much for sharing!!
awesome explanation :)
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
Thank you!
Thanks for video and very good explanation. Could you please tell me how Divergence based Domain is different from Adaptation Divergence based Domain Adaptation?
Thank you Kate!
Does these methods works well for regression problems?
Yes, but you have to look for mathematical justification from Mehryar Mohri work on domain adaptation for regression
@@gauravprasad6266 Thanks for the comment
Can I get the slides of the video? if it is available, I didn't find it on the attachment website
?????? no response !!!
i also want them
what is the use of a discriminator anyway we are going to fool the discriminator ?? what happens when we didn't use the discriminator?
👍❤
🇲🇾