Name
Abstract | ||
|---|---|---|
In this paper, we study how to use semantic relationships for image classification in order to improve the classification accuracy. We achieve the goal by imitating the human visual system which classifies categories from coarse to fine grains based on different visual features. We propose an ontological bagging algorithm where most discriminative weak attributes are automatically learned for different semantic levels by multiple instance learning and the bagging idea is applied to reduce the error propagations of hierarchical classifiers. We also leverage ontological knowledge to augment crowdsourcing annotations (e.g., a hatchback is also a vehicle) in order to train hierarchical classifiers. Our method is tested on a vehicle dataset from the popular crowdsourcing dataset ImageNet. Experimental results show that our method not only achieves state-of-the-art results but also identifies semantically meaningful visual features. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICMEW.2014.6890588 | ICME Workshops |
Keywords | Field | DocType |
ontological bagging approach,ontology,human visual system,semantic relationships,error propagations,semantic levels,crowdsourcing,image classification,visual features,ontologies (artificial intelligence),multiple instance learning,hierarchical classifiers,crowdsourcing dataset imagenet,hierarchical weak attributes,vehicle dataset,crowd sourced data,accuracy,bagging,semantics,ontologies,visualization | Ontology (information science),Ontology,Pattern recognition,Visualization,Crowdsourcing,Human visual system model,Computer science,Artificial intelligence,Contextual image classification,Discriminative model,Semantics,Machine learning | Conference |
ISSN | Citations | PageRank |
1945-7871 | 1 | 0.35 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ning Xu | 1 | 88 | 10.99 |
| Jiangping Wang | 2 | 69 | 9.25 |
| Zhaowen Wang | 3 | 1063 | 40.64 |
| Thomas S. Huang | 4 | 27815 | 2618.42 |