Electrical Engineering
      and Computer Sciences

Electrical Engineering and Computer Sciences

COLLEGE OF ENGINEERING

UC Berkeley

Incorporating Supervision for Visual Recognition and Segmentation

Alex Yu Jen Shyr

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2011-116
November 4, 2011

http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-116.pdf

Unsupervised algorithms which do not make use of labels are commonly found in computer vision and are widely applicable to all problem settings. In the presence of expert-labeled ground truth information, however, these algorithms are not optimal. Altering the unsupervised models to include labels is not always a straight forward modification. In this dissertation, we explore various ways to incorporate human supervision. We first start with the task of visual sequence recognition and demonstrate ways to effectively make use of temporal information. Next, we tackle the problem of scene segmentation and devise a novel framework to discriminatively train a generative hierarchical model with nonparametric Bayesian priors; the methodology can be easily applied to other nonparametric Bayesian models. Finally, we approach the difficult problem of object segmentation and describe how shape priors can be infused into a generative Bayesian segmentation model. We demonstrate the effectiveness of our models and algorithms on datasets which are widely used by the research community and universally regarded as difficult. The dissertation concludes with active venues for future research.

Advisor: Michael Jordan


BibTeX citation:

@phdthesis{Shyr:EECS-2011-116,
    Author = {Shyr, Alex Yu Jen},
    Title = {Incorporating Supervision for Visual Recognition and Segmentation},
    School = {EECS Department, University of California, Berkeley},
    Year = {2011},
    Month = {Nov},
    URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-116.html},
    Number = {UCB/EECS-2011-116},
    Abstract = {Unsupervised algorithms which do not make use of labels are commonly found in computer
vision and are widely applicable to all problem settings. In the presence of expert-labeled ground
truth information, however, these algorithms are not optimal. Altering the unsupervised models to
include labels is not always a straight forward modification. In this dissertation, we explore various
ways to incorporate human supervision.
We first start with the task of visual sequence recognition and demonstrate ways to effectively
make use of temporal information. Next, we tackle the problem of scene segmentation and devise
a novel framework to discriminatively train a generative hierarchical model with nonparametric
Bayesian priors; the methodology can be easily applied to other nonparametric Bayesian models.
Finally, we approach the difficult problem of object segmentation and describe how shape priors
can be infused into a generative Bayesian segmentation model. We demonstrate the effectiveness
of our models and algorithms on datasets which are widely used by the research community and
universally regarded as difficult. The dissertation concludes with active venues for future research.}
}

EndNote citation:

%0 Thesis
%A Shyr, Alex Yu Jen
%T Incorporating Supervision for Visual Recognition and Segmentation
%I EECS Department, University of California, Berkeley
%D 2011
%8 November 4
%@ UCB/EECS-2011-116
%U http://www.eecs.berkeley.edu/Pubs/TechRpts/2011/EECS-2011-116.html
%F Shyr:EECS-2011-116