A Bayesian Generative Model for Learning Semantic Hierarchies
Building fine-grained visual recognition systems that are capable of recognizing tens of thousands of categories, has received much attention in recent years. The well known semantic hierarchical structure of categories and concepts, has been shown to provide a key prior which allows for optimal pre...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2014-05-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fpsyg.2014.00417/full |
| _version_ | 1811241885770973184 |
|---|---|
| author | Roni eMittelman Min eSun Benjamin eKuipers Silvio eSavarese |
| author_facet | Roni eMittelman Min eSun Benjamin eKuipers Silvio eSavarese |
| author_sort | Roni eMittelman |
| collection | DOAJ |
| description | Building fine-grained visual recognition systems that are capable of recognizing tens of thousands of categories, has received much attention in recent years. The well known semantic hierarchical structure of categories and concepts, has been shown to provide a key prior which allows for optimal predictions. The hierarchical organization of various domains and concepts has been subject to extensive research, and led to the development of the WordNet domains hierarchy [18], which was also used to organize the images in the ImageNet [11] dataset, in which the category count approaches the human capacity. Still, for the human visual system, the form of the hierarchy must be discovered with minimal use of supervision or innate knowledge. In this work, we propose a new Bayesian generative model for learning such domain hierarchies, based on semantic input. Our model is motivated by the super-subordinate organization of domain labels and concepts that characterizes WordNet, and accounts for several important challenges: maintaining context information when progressing deeper into the hierarchy, learning a coherent semantic concept for each node, and modeling uncertainty in the perception process. |
| first_indexed | 2024-04-12T13:42:55Z |
| format | Article |
| id | doaj.art-657e0b6351e644cfaa62c66e47bd744e |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-04-12T13:42:55Z |
| publishDate | 2014-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-657e0b6351e644cfaa62c66e47bd744e2022-12-22T03:30:47ZengFrontiers Media S.A.Frontiers in Psychology1664-10782014-05-01510.3389/fpsyg.2014.0041762784A Bayesian Generative Model for Learning Semantic HierarchiesRoni eMittelman0Min eSun1Benjamin eKuipers2Silvio eSavarese3University of MichiganUniversity of WashingtonUniversity of MichiganStanford UniversityBuilding fine-grained visual recognition systems that are capable of recognizing tens of thousands of categories, has received much attention in recent years. The well known semantic hierarchical structure of categories and concepts, has been shown to provide a key prior which allows for optimal predictions. The hierarchical organization of various domains and concepts has been subject to extensive research, and led to the development of the WordNet domains hierarchy [18], which was also used to organize the images in the ImageNet [11] dataset, in which the category count approaches the human capacity. Still, for the human visual system, the form of the hierarchy must be discovered with minimal use of supervision or innate knowledge. In this work, we propose a new Bayesian generative model for learning such domain hierarchies, based on semantic input. Our model is motivated by the super-subordinate organization of domain labels and concepts that characterizes WordNet, and accounts for several important challenges: maintaining context information when progressing deeper into the hierarchy, learning a coherent semantic concept for each node, and modeling uncertainty in the perception process.http://journal.frontiersin.org/Journal/10.3389/fpsyg.2014.00417/fullsemanticsBayesian inferencebayesian models of cognitionNonparametric Bayeshierarchical clustering |
| spellingShingle | Roni eMittelman Min eSun Benjamin eKuipers Silvio eSavarese A Bayesian Generative Model for Learning Semantic Hierarchies Frontiers in Psychology semantics Bayesian inference bayesian models of cognition Nonparametric Bayes hierarchical clustering |
| title | A Bayesian Generative Model for Learning Semantic Hierarchies |
| title_full | A Bayesian Generative Model for Learning Semantic Hierarchies |
| title_fullStr | A Bayesian Generative Model for Learning Semantic Hierarchies |
| title_full_unstemmed | A Bayesian Generative Model for Learning Semantic Hierarchies |
| title_short | A Bayesian Generative Model for Learning Semantic Hierarchies |
| title_sort | bayesian generative model for learning semantic hierarchies |
| topic | semantics Bayesian inference bayesian models of cognition Nonparametric Bayes hierarchical clustering |
| url | http://journal.frontiersin.org/Journal/10.3389/fpsyg.2014.00417/full |
| work_keys_str_mv | AT roniemittelman abayesiangenerativemodelforlearningsemantichierarchies AT minesun abayesiangenerativemodelforlearningsemantichierarchies AT benjaminekuipers abayesiangenerativemodelforlearningsemantichierarchies AT silvioesavarese abayesiangenerativemodelforlearningsemantichierarchies AT roniemittelman bayesiangenerativemodelforlearningsemantichierarchies AT minesun bayesiangenerativemodelforlearningsemantichierarchies AT benjaminekuipers bayesiangenerativemodelforlearningsemantichierarchies AT silvioesavarese bayesiangenerativemodelforlearningsemantichierarchies |