Novel Meta-Learning Techniques for the Multiclass Image Classification Problem
Open Access
Abstract
Multiclass image classification is a complex task that has been thoroughly investigated in the past. Decomposition-based strategies are commonly employed to address it. Typically, these methods divide the original problem into smaller, potentially simpler problems, allowing the application of numerous well-established learning algorithms that may not apply directly to the original task. This work focuses on the efficiency of decomposition-based methods and proposes several improvements to the meta-learning level. In this paper, four methods for optimizing the ensemble phase of multiclass classification are introduced. The first demonstrates that employing a mixture of experts scheme can drastically reduce the number of operations in the training phase by eliminating redundant learning processes in decomposition-based techniques for multiclass problems. The second technique for combining learner-based outcomes relies on Bayes’ theorem. Combining the Bayes rule with arbitrary decompositions reduces training complexity relative to the number of classifiers even further. Two additional methods are also proposed for increasing the final classification accuracy by decomposing the initial task into smaller ones and ensembling the output of the base learners along with that of a multiclass classifier. Finally, the proposed novel meta-learning techniques are evaluated on four distinct datasets of varying classification difficulty. In every case, the proposed methods present a substantial accuracy improvement over existing traditional image classification techniques.Keywords
Funding Information
- European Union (T1EDK - 03110)
- Greek national funds (T1EDK - 03110)
- Operational Program Competitiveness, Entrepreneurship, and Innovation (T1EDK - 03110)
This publication has 26 references indexed in Scilit:
- Ensemble learning for data stream analysis: A surveyInformation Fusion, 2017
- Application of machine learning on brain cancer multiclass classificationAIP Conference Proceedings, 2017
- Deep Residual Learning for Image Recognition2016
- Hybrid Ensemble of classifiers using voting2015
- Multi-column deep neural networks for image classification2012
- An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemesPattern Recognition, 2011
- A systematic analysis of performance measures for classification tasksInformation Processing & Management, 2009
- ImageNet: A large-scale hierarchical image database2009
- On the Boosting Ability of Top–Down Decision Tree Learning AlgorithmsJournal of Computer and System Sciences, 1999
- Stacked generalizationNeural Networks, 1992