edoc

Greedy Structure Learning of Hierarchical Compositional Models

Kortylewski, Adam and Wieczorek, Aleksander and Wieser, Mario and Blumer, Clemens and Parbhoo, Sonali and Morel-Forster, Andreas and Roth, Volker and Vetter, Thomas. (2019) Greedy Structure Learning of Hierarchical Compositional Models. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 11612-11621.

[img] PDF - Accepted Version
838Kb

Official URL: https://edoc.unibas.ch/73939/

Downloads: Statistics Overview

Abstract

In this work, we consider the problem of learning a hierarchical generative model of an object from a set of im-ages which show examples of the object in the presenceof variable background clutter. Existing approaches tothis problem are limited by making strong a-priori assump-tions about the object’s geometric structure and require seg-mented training data for learning. In this paper, we pro-pose a novel framework for learning hierarchical compo-sitional models (HCMs) which do not suffer from the men-tioned limitations. We present a generalized formulation ofHCMs and describe a greedy structure learning frameworkthat consists of two phases: Bottom-up part learning andtop-down model composition. Our framework integratesthe foreground-background segmentation problem into thestructure learning task via a background model. As a result, we can jointly optimize for the number of layers in thehierarchy, the number of parts per layer and a foreground-background segmentation based on class labels only. Weshow that the learned HCMs are semantically meaningfuland achieve competitive results when compared to othergenerative object models at object classification on a stan-dard transfer learning dataset.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Computergraphik Bilderkennung (Vetter)
05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Datenanalyse (Roth)
UniBasel Contributors:Roth, Volker and Kortylewski, Adam and Wieczorek, Aleksander and Wieser, Mario and Blumer, Clemens and Parbhoo, Sonali and Morel, Andreas and Vetter, Thomas
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:IEEE
Note:Publication type according to Uni Basel Research Database: Conference paper
Language:English
Related URLs:
Identification Number:
Last Modified:31 Jan 2020 14:21
Deposited On:31 Jan 2020 13:48

Repository Staff Only: item control page