Clustered Exemplar-SVM: Discovering sub-categories for visual recognition

Autor:	Greg Mori, Nataliya Shapovalova
Rok vydání:	2015
Předmět:	Visual recognition Support vector machine ComputingMethodologies_PATTERNRECOGNITION Contextual image classification business.industry Computer science Pattern recognition Artificial intelligence business Machine learning computer.software_genre Classifier (UML) computer
Zdroj:	ICIP
DOI:	10.1109/icip.2015.7350766
Popis:	We present a novel algorithm for image classification that is targeted to capture class variability. A single model is often not sufficient to represent a category since categories can vary from large semantic classes to fine-grained sub-categories. Instead, we develop a representation based on discovering visually similar sub-categories within a given class. We introduce a novel Clustered Exemplar SVM classifier which incorporates data-driven and exemplar focused discovery. Semi-supervised learning is employed for training each C-eSVM classifier. We evaluate our approach on two datasets and demonstrate the efficacy of our method over standard Exemplar SVM.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::f5825bb04088e6e3f0cc0ea114608520 https://doi.org/10.1109/icip.2015.7350766 Zobrazit plný text záznamu