Data Driven Visual Recognition

Open Access
Author:
Description:
This thesis is mostly about supervised visual recognition problems. Based on a general definition of categories, the contents are divided into two parts: one which models categories and one which is not category based. We are interested in data driven solutions for both kinds of problems. In the category-free part, we study novelty detection in temporal and spatial domains as a category-free recognition problem. Using data driven models, we demonstrate that based on a few reference exemplars, our methods are able to detect novelties in ego-motions of people, and changes in the static environments surrounding them. In the category level part, we study object recognition. We consider both object category classification and localization, and propose scalable data driven approaches for both problems. A mixture of parametric classifiers, initialized with a sophisticated clustering of the training data, is demonstrated to adapt to the data better than various baselines such as the same model initialized with less subtly designed procedures. A nonparametric large margin classifier is introduced and demonstrated to have a multitude of advantages in comparison to its competitors: better training and testing time costs, the ability to make use of indefinite/invariant and deformable similarity measures, and adaptive complexity are the main features of the proposed model. We also propose a rather realistic model of recognition problems, which quantifies the interplay between representations, classifiers, and recognition performances. Based on data-describing measures which are aggregates of pairwise similarities of the training data, our model characterizes and describes the distributions of training exemplars. The measures are shown to capture many aspects of the difficulty of categorization problems and correlate significantly to the observed recognition performances. Utilizing these measures, the model predicts the performance of particular classifiers on distributions similar to the training data. These predictions, ...
Publisher:
KTH, Datorseende och robotik, CVAP
Year of Publication:
2014
Document Type:
Doctoral thesis, comprehensive summary ; info:eu-repo/semantics/doctoralThesis ; text ; [Doctoral and postdoctoral thesis]
Language:
eng
Subjects:
Visual Recognition ; Data Driven ; Supervised Learning ; Mixture Models ; Non-Parametric Models ; Category Recognition ; Novelty Detection ; Computer Vision and Robotics (Autonomous Systems) ; Datorseende och robotik (autonoma system)
DDC:
004 Data processing & computer science (computed)
Rights:
info:eu-repo/semantics/openAccess
URL:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-145865
Content Provider:
Kungliga Tekniska Högskolan, Stockholm: KTHs Publikationsdatabas DiVA
Further nameRoyal Institute of Technology, Stockholm: KTHs Publication Database DiVA  Flag of Sweden