DALI 2018 - Andreas Geiger: How to Satisfy the Thirst for Data
Offered By: Andreas Geiger via YouTube
Course Description
Overview
Explore cutting-edge approaches to addressing data scarcity in machine learning with Andreas Geiger's insightful conference talk. Delve into innovative techniques such as specialized architectures, soft constraints, self-supervision, mixed reality, and label transfer. Gain valuable insights on improving optical flow algorithms and enhancing generalization capabilities in data-hungry applications. Discover how these methods can revolutionize the field of computer vision and help overcome the challenges posed by limited labeled datasets.
Syllabus
Intro
The problem
Optical flow
Specialized architectures
Soft constraints
Self supervision
Mixed Reality
Label Transfer
Generalization
Taught by
Andreas Geiger
Related Courses
Stereo Vision, Dense Motion & TrackingUniversity at Buffalo via Coursera Computer Vision - Object Tracking with OpenCV and Python
Coursera Project Network via Coursera 3D Reconstruction - Multiple Viewpoints
Columbia University via Coursera Computer Vision for Visual Effects Lectures Spring 2014
Rensselaer Polytechnic Institute via YouTube Object Tracking and Motion Detection with Computer Vision
MathWorks via Coursera