Completed
- Intro
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
Author Interview - VOS- Learning What You Don't Know by Virtual Outlier Synthesis
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro
- 2 - What was the motivation behind this paper?
- 3 - Why object detection?
- 4 - What's the connection to energy-based models?
- 5 - Is a Gaussian mixture model appropriate for high-dimensional data?
- 6 - What are the most important components of the method?
- 7 - What are the downstream effects of the regularizer?
- 8 - Are there severe trade-offs to outlier detection?
- 9 - Main experimental takeaways?
- 10 - Why do outlier detection in the last layer?
- 11 - What does it take to finish a research projects successfully?