Fine-grained semi-supervised labeling of large shape collections

Abstract

In this paper we consider the problem of classifying shapes within a given category (e.g., chairs) into finer-grained classes (e.g., chairs with arms, rocking chairs, swivel chairs). We introduce a multi-label (i.e., shapes can belong to multiple classes) semi-supervised approach that takes as input a large shape collection of a given category with associated sparse and noisy labels, and outputs cleaned and complete labels for each shape. The key idea of the proposed approach is to jointly learn a distance metric for each class which captures the underlying geometric similarity within that class, e.g., the distance metric for swivel chairs evaluates the global geometric resemblance of chair bases. We show how to achieve this objective by first geometrically aligning the input shapes, and then learning the class-specific distance metrics by exploiting the feature consistency provided by this alignment. The learning objectives consider both labeled data and the mutual relations between the distance metrics. Given the learned metrics, we apply a graph-based semi-supervised classification technique to generate the final classification results.

Document Details

Document Type
Pub Defense Publication
Publication Date
Nov 01, 2013
Source ID
10.1145/2508363.2508364

Entities

People

  • Hao Su
  • Leonidas J. Guibas
  • Qi-xing Huang

Organizations

  • Air Force Office of Scientific Research
  • Division of Computing and Communication Foundations
  • Google
  • National Science Foundation
  • Office of Naval Research
  • Stanford University

Tags

Fields of Study

  • Computer science

Readers

  • Defense Acquisition Program Management
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks