Active Sample Selection and Correction Propagation on a Gradually-Augmented Graph

Abstract

When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small number of initial annotations. To address this issue with minimal human interventions, we propose (i) a sample selection criterion used for active query of informative samples by minimizing the expected prediction error, and (ii) an efficient correction propagation method that propagates human correction on selected samples over a gradually-augmented graph to unlabeled samples without rebuilding the affinity graph. Experimental results conducted on three real world datasets validate that our active sample selection and correction propagation algorithm quickly reaches high quality classification results with minimal human interventions.

Meeting Name

IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2015: Jun. 7-12, Boston, MA)

Department(s)

Computer Science

Keywords and Phrases

Classification (of Information); Computer Vision; Graphic Methods; Supervised Learning; Human Intervention; Manifold Structures; Prediction Errors; Propagation Algorithm; Propagation Method; Real-World Datasets; Semi-Supervised Learning Methods; Unlabeled Samples; Pattern Recognition

International Standard Book Number (ISBN)

978-1467369640

International Standard Serial Number (ISSN)

1063-6919

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2015 IEEE Computer Society, All rights reserved.

Publication Date

01 Jun 2015

Link to Full Text

Share

 
COinS