Incremental learning framework for indoor scene recognition

This paper presents a novel framework for online incremental place recognition in an indoor environment. The framework addresses the scenario in which scene images are gradually obtained during long-term operation in the real-world indoor environment. Multiple users may interact with the classificat...

Full description

Saved in:
Bibliographic Details
Main Authors: Aram Kawewong, Rapeeporn Pimpup, Osamu Hasegawa
Format: Conference Proceeding
Published: 2018
Online Access:https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84893409703&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/47418
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Chiang Mai University
id th-cmuir.6653943832-47418
record_format dspace
spelling th-cmuir.6653943832-474182018-04-25T08:39:50Z Incremental learning framework for indoor scene recognition Aram Kawewong Rapeeporn Pimpup Osamu Hasegawa This paper presents a novel framework for online incremental place recognition in an indoor environment. The framework addresses the scenario in which scene images are gradually obtained during long-term operation in the real-world indoor environment. Multiple users may interact with the classification system and confirm either current or past prediction results; the system then immediately updates itself to improve the classification system. This framework is based on the proposed n-value self-organizing and incremental neural network (n-SOINN), which has been derived by modifying the original SOINN to be appropriate for use in scene recognition. The evaluation was performed on the standard MIT 67-category indoor scene dataset and shows that the proposed framework achieves the same accuracy as that of the state-of-the-art offline method, while the computation time of the proposed framework is significantly faster and fully incremental update is allowed. Additionally, a small extra set of training samples is incrementally given to the system to simulate the incremental learning situation. The result shows that the proposed framework can leverage such additional samples and achieve the state-of-the-art result. Copyright © 2013, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. 2018-04-25T08:39:50Z 2018-04-25T08:39:50Z 2013-12-01 Conference Proceeding 2-s2.0-84893409703 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84893409703&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/47418
institution Chiang Mai University
building Chiang Mai University Library
country Thailand
collection CMU Intellectual Repository
description This paper presents a novel framework for online incremental place recognition in an indoor environment. The framework addresses the scenario in which scene images are gradually obtained during long-term operation in the real-world indoor environment. Multiple users may interact with the classification system and confirm either current or past prediction results; the system then immediately updates itself to improve the classification system. This framework is based on the proposed n-value self-organizing and incremental neural network (n-SOINN), which has been derived by modifying the original SOINN to be appropriate for use in scene recognition. The evaluation was performed on the standard MIT 67-category indoor scene dataset and shows that the proposed framework achieves the same accuracy as that of the state-of-the-art offline method, while the computation time of the proposed framework is significantly faster and fully incremental update is allowed. Additionally, a small extra set of training samples is incrementally given to the system to simulate the incremental learning situation. The result shows that the proposed framework can leverage such additional samples and achieve the state-of-the-art result. Copyright © 2013, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
format Conference Proceeding
author Aram Kawewong
Rapeeporn Pimpup
Osamu Hasegawa
spellingShingle Aram Kawewong
Rapeeporn Pimpup
Osamu Hasegawa
Incremental learning framework for indoor scene recognition
author_facet Aram Kawewong
Rapeeporn Pimpup
Osamu Hasegawa
author_sort Aram Kawewong
title Incremental learning framework for indoor scene recognition
title_short Incremental learning framework for indoor scene recognition
title_full Incremental learning framework for indoor scene recognition
title_fullStr Incremental learning framework for indoor scene recognition
title_full_unstemmed Incremental learning framework for indoor scene recognition
title_sort incremental learning framework for indoor scene recognition
publishDate 2018
url https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84893409703&origin=inward
http://cmuir.cmu.ac.th/jspui/handle/6653943832/47418
_version_ 1681423057229447168