Selectively guiding visual concept discovery

Abstract

Labeling data to train visual concept classifiers requires significant human effort. Active learning addresses labeling overhead by selecting a meaningful subset of data, but often these approaches assume that the set of visual concepts is known in advance. Clustering approaches perform bottom-up discovery of concepts, and reduce labeling effort by moving… (More)
DOI: 10.1109/WACV.2014.6836093

6 Figures and Tables

Topics

  • Presentations referencing similar topics