Multi-layer feature extractions for image classification - Knowledge from deep CNNs

Kazuya Ueki; Tetsunori Kobayashi

doi:10.1109/IWSSIP.2015.7313925

Multi-layer feature extractions for image classification - Knowledge from deep CNNs

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Recently, there has been considerable research into the application of deep learning to image recognition. Notably, deep convolutional neural networks (CNNs) have achieved excellent performance in a number of image classification tasks, compared with conventional methods based on techniques such as Bag-of-Features (BoF) using local descriptors. In this paper, to cultivate a better understanding of the structure of CNN, we focus on the characteristics of deep CNNs, and adapt them to SIFT+BoF-based methods to improve the classification accuracy. We introduce the multi-layer structure of CNNs into the classification pipeline of the BoF framework, and conduct experiments to confirm the effectiveness of this approach using a fine-grained visual categorization dataset. The results show that the average classification rate is improved from 52.4% to 69.8%.

Original language	English
Title of host publication	2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	9-12
Number of pages	4
ISBN (Print)	9781467383530
DOIs	https://doi.org/10.1109/IWSSIP.2015.7313925
Publication status	Published - 2015 Oct 30
Event	22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015 - London, United Kingdom Duration: 2015 Sept 10 → 2015 Sept 12

Other

Other	22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015
Country/Territory	United Kingdom
City	London
Period	15/9/10 → 15/9/12

Keywords

Bag-of-Features
Deep learning
Feature extraction
Fine-grained visual categorization
Generic object recognition

ASJC Scopus subject areas

Computer Networks and Communications
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/IWSSIP.2015.7313925

Cite this

Multi-layer feature extractions for image classification - Knowledge from deep CNNs. / Ueki, Kazuya; Kobayashi, Tetsunori.

2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 9-12 7313925.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ueki, K & Kobayashi, T 2015, Multi-layer feature extractions for image classification - Knowledge from deep CNNs. in 2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015., 7313925, Institute of Electrical and Electronics Engineers Inc., pp. 9-12, 22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015, London, United Kingdom, 15/9/10. https://doi.org/10.1109/IWSSIP.2015.7313925

@inproceedings{5ebb651d3d0645c39374af51f8298059,

title = "Multi-layer feature extractions for image classification - Knowledge from deep CNNs",

abstract = "Recently, there has been considerable research into the application of deep learning to image recognition. Notably, deep convolutional neural networks (CNNs) have achieved excellent performance in a number of image classification tasks, compared with conventional methods based on techniques such as Bag-of-Features (BoF) using local descriptors. In this paper, to cultivate a better understanding of the structure of CNN, we focus on the characteristics of deep CNNs, and adapt them to SIFT+BoF-based methods to improve the classification accuracy. We introduce the multi-layer structure of CNNs into the classification pipeline of the BoF framework, and conduct experiments to confirm the effectiveness of this approach using a fine-grained visual categorization dataset. The results show that the average classification rate is improved from 52.4% to 69.8%.",

keywords = "Bag-of-Features, Deep learning, Feature extraction, Fine-grained visual categorization, Generic object recognition",

author = "Kazuya Ueki and Tetsunori Kobayashi",

year = "2015",

month = oct,

day = "30",

doi = "10.1109/IWSSIP.2015.7313925",

language = "English",

isbn = "9781467383530",

pages = "9--12",

booktitle = "2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015 ; Conference date: 10-09-2015 Through 12-09-2015",

}

TY - GEN

T1 - Multi-layer feature extractions for image classification - Knowledge from deep CNNs

AU - Ueki, Kazuya

AU - Kobayashi, Tetsunori

PY - 2015/10/30

Y1 - 2015/10/30

N2 - Recently, there has been considerable research into the application of deep learning to image recognition. Notably, deep convolutional neural networks (CNNs) have achieved excellent performance in a number of image classification tasks, compared with conventional methods based on techniques such as Bag-of-Features (BoF) using local descriptors. In this paper, to cultivate a better understanding of the structure of CNN, we focus on the characteristics of deep CNNs, and adapt them to SIFT+BoF-based methods to improve the classification accuracy. We introduce the multi-layer structure of CNNs into the classification pipeline of the BoF framework, and conduct experiments to confirm the effectiveness of this approach using a fine-grained visual categorization dataset. The results show that the average classification rate is improved from 52.4% to 69.8%.

AB - Recently, there has been considerable research into the application of deep learning to image recognition. Notably, deep convolutional neural networks (CNNs) have achieved excellent performance in a number of image classification tasks, compared with conventional methods based on techniques such as Bag-of-Features (BoF) using local descriptors. In this paper, to cultivate a better understanding of the structure of CNN, we focus on the characteristics of deep CNNs, and adapt them to SIFT+BoF-based methods to improve the classification accuracy. We introduce the multi-layer structure of CNNs into the classification pipeline of the BoF framework, and conduct experiments to confirm the effectiveness of this approach using a fine-grained visual categorization dataset. The results show that the average classification rate is improved from 52.4% to 69.8%.

KW - Bag-of-Features

KW - Deep learning

KW - Feature extraction

KW - Fine-grained visual categorization

KW - Generic object recognition

UR - http://www.scopus.com/inward/record.url?scp=84961718052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961718052&partnerID=8YFLogxK

U2 - 10.1109/IWSSIP.2015.7313925

DO - 10.1109/IWSSIP.2015.7313925

M3 - Conference contribution

AN - SCOPUS:84961718052

SN - 9781467383530

SP - 9

EP - 12

BT - 2015 22nd International Conference on Systems, Signals and Image Processing - Proceedings of IWSSIP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 22nd International Conference on Systems, Signals and Image Processing, IWSSIP 2015

Y2 - 10 September 2015 through 12 September 2015

ER -

Multi-layer feature extractions for image classification - Knowledge from deep CNNs

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this