Structured Prediction Models for High-level Computer Vision Tasks

186 views · Published 17 August 2016 · 56:37 · Indexed 10 November 2026

Channel: Microsoft Research · 2016 · Science & Technology

Watch on YouTube

Rich statistical models have revolutionized computer vision research:    graphical models and structured prediction in particular are now commonly used  tools to address hard computer vision problems.  I discuss what distinguishes  these computer vision problems from other machine learning problems and how  this poses unique challenges.    I argue that most computer vision models are misspecified and discuss the  consequences of popular estimators in this case, concluding that we either  have to use non-parametric models or use estimators robust to  misspecification.    As one possible solution, I propose a novel discrete random field model  applicable to a large number of computer vision tasks.  The model is  conditionally specified, non-parametric, and able to represent complex label  interactions, yet it can be trained from hundreds of images in minutes on a  single machine.

More from this channel