Advanced Methods and Deep Learning in Computer Vision

Chapter 3: Learning with limited supervision

Static and dynamic tasks

Sujoy Paul^a,c; Amit K. Roy-Chowdhury^b    aGoogle Research, Bangalore, India^bUniversity of California, Riverside, Electrical and Computer Engineering, Riverside, CA, United States^cThis work was done when the author was at UC Riverside.

Abstract

The recent successes in computer vision, and machine learning in general, have been mostly around using a huge corpus of intricately labeled data for training models. But, in real-world cases, acquiring such large datasets will require a lot of manual annotation, which may be strenuous, out of budget, or even prone to errors. Thus, it is necessary to develop methods where the amount of labeled data is minimized or can be obtained at low to ...