The Role of Data and Models for Deep-Learning Based Image Reconstruction

The Role of Data and Models for Deep-Learning Based Image Reconstruction

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Test time training

15 of 18

15 of 18

Test time training

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Role of Data and Models for Deep-Learning Based Image Reconstruction

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Scaling language models
  3. 3 Data set sizes in imaging tasks are small
  4. 4 Expected performance behavior
  5. 5 U-net-based denoising
  6. 6 U-net-based accelerated MRI
  7. 7 Swin transformer based denoising
  8. 8 Reconstruction methods
  9. 9 What we might expect
  10. 10 Dataset shift
  11. 11 Adversarially filtered shift
  12. 12 Goal: improve performance unter distribution shifts
  13. 13 For classification problems, "natural distribution shifts are an open research problem"
  14. 14 Improving performance for 11-minimization is easy
  15. 15 Test time training
  16. 16 Closing the distribution shift performance gap for anatomy shift
  17. 17 Closing the distribution shift performance gap with test-time-training
  18. 18 References

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.