SCITEPRESS (original) (raw)
Paper
Deep Spatial Pyramid Match Kernel for Scene Classification
Topics: Classification; Deep Learning; Image Understanding; Kernel Methods
Shikha Gupta 1 ; Deepak Kumar Pradhan 2 ; Dileep Aroor Dinesh 1 and Veena Thenkanidiyoor 2
Affiliations: 1 Indian Institute of Technology Mandi, India ; 2 National Institute of Technology Goa, India
Keyword(s): Scene Classification, Dynamic Kernel, Set of Varying Length Feature Map, Support Vector Machine, Convolutional Neural Network, Deep Spatial Pyramid Match Kernel.
RelatedOntology Subjects/Areas/Topics: Applications ; Classification ; Computer Vision, Visualization and Computer Graphics ; Image Understanding ; Kernel Methods ; Pattern Recognition ; Theory and Methods
Abstract: Several works have shown that Convolutional Neural Networks (CNNs) can be easily adapted to different datasets and tasks. However, for extracting the deep features from these pre-trained deep CNNs a fixedsize (e.g., 227227) input image is mandatory. Now the state-of-the-art datasets like MIT-67 and SUN-397 come with images of different sizes. Usage of CNNs for these datasets enforces the user to bring different sized images to a fixed size either by reducing or enlarging the images. The curiosity is obvious that “Isn’t the conversion to fixed size image is lossy ?”. In this work, we provide a mechanism to keep these lossy fixed size images aloof and process the images in its original form to get set of varying size deep feature maps, hence being lossless. We also propose deep spatial pyramid match kernel (DSPMK) which amalgamates set of varying size deep feature maps and computes a matching score between the samples. Proposed DSPMK act as a dynamic kernel in the classificat ion framework of scene dataset using support vector machine. We demonstrated the effectiveness of combining the power of varying size CNN-based set of deep feature maps with dynamic kernel by achieving state-of-the-art results for high-level visual recognition tasks such as scene classification on standard datasets like MIT67 and SUN397. (More)
Several works have shown that Convolutional Neural Networks (CNNs) can be easily adapted to different
datasets and tasks. However, for extracting the deep features from these pre-trained deep CNNs a fixedsize
(e.g., 227227) input image is mandatory. Now the state-of-the-art datasets like MIT-67 and SUN-397
come with images of different sizes. Usage of CNNs for these datasets enforces the user to bring different
sized images to a fixed size either by reducing or enlarging the images. The curiosity is obvious that “Isn’t
the conversion to fixed size image is lossy ?”. In this work, we provide a mechanism to keep these lossy fixed
size images aloof and process the images in its original form to get set of varying size deep feature maps,
hence being lossless. We also propose deep spatial pyramid match kernel (DSPMK) which amalgamates set
of varying size deep feature maps and computes a matching score between the samples. Proposed DSPMK
act as a dynamic kernel in the classification framework of scene dataset using support vector machine. We
demonstrated the effectiveness of combining the power of varying size CNN-based set of deep feature maps
with dynamic kernel by achieving state-of-the-art results for high-level visual recognition tasks such as scene
classification on standard datasets like MIT67 and SUN397.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guests can use SciTePress Digital Library without having a SciTePress account. However, guests have limited access to downloading full text versions of papers and no access to special options.
Guest:Register as new SciTePress user now for free.
Download limit per month - 500 recent papers or 4000 papers more than 2 years old.
SciTePress user: please login.
You are not signed in, therefore limits apply to your IP address 136.107.100.216
In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total
Paper citation in several formats:
Gupta, S., Pradhan, D. K., Aroor Dinesh, D. and Thenkanidiyoor, V. (2018). Deep Spatial Pyramid Match Kernel for Scene Classification. In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-276-9; ISSN 2184-4313, SciTePress, pages 141-148. DOI: 10.5220/0006596101410148
@conference{icpram18,
author={Shikha Gupta and Deepak Kumar Pradhan and Dileep {Aroor Dinesh} and Veena Thenkanidiyoor},
title={Deep Spatial Pyramid Match Kernel for Scene Classification},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2018},
pages={141-148},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006596101410148},
isbn={978-989-758-276-9},
issn={2184-4313},
}
TY - CONF
JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Deep Spatial Pyramid Match Kernel for Scene Classification
SN - 978-989-758-276-9
IS - 2184-4313
AU - Gupta, S.
AU - Pradhan, D.
AU - Aroor Dinesh, D.
AU - Thenkanidiyoor, V.
PY - 2018
SP - 141
EP - 148
DO - 10.5220/0006596101410148
PB - SciTePress