Fine-grained classification via mixture of deep convolutional neural networks

Zongyuan Ge, Alex Bewley, Christopher McCool, Peter Corke, Ben Upcroft, Conrad Sanderson

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.

Original languageEnglish
Title of host publication2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)
EditorsGreg Mori, Robert Pless, Scott McCloskey, Rahul Sukthankar
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781509006410
ISBN (Print)9781509006427
DOIs
Publication statusPublished - 23 May 2016
Externally publishedYes
EventIEEE Winter Conference on Applications of Computer Vision 2016 - Lake Placid, United States of America
Duration: 7 Mar 20169 Mar 2016
Conference number: 5th
http://www.wacv16.org/
http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=46372&copyownerid=26710
http://wacv16.wacv.net/

Conference

ConferenceIEEE Winter Conference on Applications of Computer Vision 2016
Abbreviated titleWACV 2016
CountryUnited States of America
CityLake Placid
Period7/03/169/03/16
Internet address

Cite this

Ge, Z., Bewley, A., McCool, C., Corke, P., Upcroft, B., & Sanderson, C. (2016). Fine-grained classification via mixture of deep convolutional neural networks. In G. Mori, R. Pless, S. McCloskey, & R. Sukthankar (Eds.), 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016) [7477700] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/WACV.2016.7477700
Ge, Zongyuan ; Bewley, Alex ; McCool, Christopher ; Corke, Peter ; Upcroft, Ben ; Sanderson, Conrad. / Fine-grained classification via mixture of deep convolutional neural networks. 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016). editor / Greg Mori ; Robert Pless ; Scott McCloskey ; Rahul Sukthankar. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2016.
@inproceedings{fe5f4a2d9a8340c497c79768d25efb11,
title = "Fine-grained classification via mixture of deep convolutional neural networks",
abstract = "We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7{\%} and achieves state-of-the-art results on two datasets.",
author = "Zongyuan Ge and Alex Bewley and Christopher McCool and Peter Corke and Ben Upcroft and Conrad Sanderson",
year = "2016",
month = "5",
day = "23",
doi = "10.1109/WACV.2016.7477700",
language = "English",
isbn = "9781509006427",
editor = "Mori, {Greg } and Robert Pless and Scott McCloskey and Rahul Sukthankar",
booktitle = "2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Ge, Z, Bewley, A, McCool, C, Corke, P, Upcroft, B & Sanderson, C 2016, Fine-grained classification via mixture of deep convolutional neural networks. in G Mori, R Pless, S McCloskey & R Sukthankar (eds), 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)., 7477700, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, IEEE Winter Conference on Applications of Computer Vision 2016, Lake Placid, United States of America, 7/03/16. https://doi.org/10.1109/WACV.2016.7477700

Fine-grained classification via mixture of deep convolutional neural networks. / Ge, Zongyuan; Bewley, Alex; McCool, Christopher; Corke, Peter; Upcroft, Ben; Sanderson, Conrad.

2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016). ed. / Greg Mori; Robert Pless; Scott McCloskey; Rahul Sukthankar. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. 7477700.

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Fine-grained classification via mixture of deep convolutional neural networks

AU - Ge, Zongyuan

AU - Bewley, Alex

AU - McCool, Christopher

AU - Corke, Peter

AU - Upcroft, Ben

AU - Sanderson, Conrad

PY - 2016/5/23

Y1 - 2016/5/23

N2 - We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.

AB - We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations and small inter-class variations. To overcome these problems our proposed MixDCNN system partitions images into K subsets of similar images and learns an expert DCNN for each subset. The output from each of the K DCNNs is combined to form a single classification decision. In contrast to previous techniques, we provide a formulation to perform joint end-to-end training of the K DCNNs simultaneously. Extensive experiments, on three datasets using two network structures (AlexNet and GoogLeNet), show that the proposed MixDCNN system consistently outperforms other methods. It provides a relative improvement of 12.7% and achieves state-of-the-art results on two datasets.

UR - http://www.scopus.com/inward/record.url?scp=84977646599&partnerID=8YFLogxK

U2 - 10.1109/WACV.2016.7477700

DO - 10.1109/WACV.2016.7477700

M3 - Conference Paper

SN - 9781509006427

BT - 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)

A2 - Mori, Greg

A2 - Pless, Robert

A2 - McCloskey, Scott

A2 - Sukthankar, Rahul

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Ge Z, Bewley A, McCool C, Corke P, Upcroft B, Sanderson C. Fine-grained classification via mixture of deep convolutional neural networks. In Mori G, Pless R, McCloskey S, Sukthankar R, editors, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2016. 7477700 https://doi.org/10.1109/WACV.2016.7477700