Making Our Models Robust to Changing Visual Environments

Making Our Models Robust to Changing Visual Environments

Andreas Geiger via YouTube Direct link

Intro

1 of 26

1 of 26

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Making Our Models Robust to Changing Visual Environments

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

  1. 1 Intro
  2. 2 Benchmark Performance
  3. 3 Dataset Bias
  4. 4 Classic Domain Adaptation
  5. 5 Deep Domain Adaptation
  6. 6 Discrepancy Between Source and Target
  7. 7 Domain Adversarial Optimization
  8. 8 Domain Adversarial Adaptation
  9. 9 Standard GAN Model
  10. 10 CycleGAN for Domain Adaptation
  11. 11 Failures of Image to Image Translation
  12. 12 Adaptation Results: Digit Recognition
  13. 13 Adaptation of Semantic Segmentation
  14. 14 Cross-city Adaptation
  15. 15 Cross Season Adaptation
  16. 16 Cross Season Pixel Adaptation
  17. 17 Synthetic to Real Pixel Adaptation
  18. 18 Summary: Adversarial Domain Adaptation
  19. 19 Continuous Learning
  20. 20 Continuous Unsupervised Adaptation
  21. 21 Experiment: MNIST Rotations
  22. 22 Replay to Remember: MNIST Rotations
  23. 23 Adapt vs Remember: MNIST Rotations
  24. 24 Evaluate MNIST 135 after all rotations
  25. 25 Summary Batch Adaptation
  26. 26 Summary Continuous Adaptation

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.