Using node relationships for hierarchical classification
Authors:
- 19 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 514-518
Abstract
Hierarchical classification is a computational efficient approach for large-scale image classification. The main challenging issue of this approach is to deal with error propagation. Irrelevant branching decision made at a parent node cannot be corrected at its child nodes in traversing the tree for classification. This paper presents a novel approach to reduce branching error at a node by taking its relative relationship into account. Given a node on the tree, we model each candidate branch by considering classification response of its child nodes, grandchild nodes and their differences with siblings. A maximum margin classifier is then applied to select the most discriminating candidate. Our proposed approach outperforms related approaches on Caltech-256, SUN-397 and ILSVRC2010-1K.Keywords
This publication has 6 references indexed in Scilit:
- Generalized Sparselet Models for Real-Time Multiclass Object RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Find the Best Path: An Efficient and Accurate Classifier for Image Hierarchies2013
- Good Practice in Large-Scale Learning for Image ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Large multi-class image categorization with ensembles of label trees2013
- Vlfeat2010
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006