Fine-grained classification via mixture of deep convolutional neural networks

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

doi:10.1109/WACV.2016.7477700

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 proceeding › Conference Paper › Research › peer-review

37 Citations (Scopus)

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 language	English
Title of host publication	2016 IEEE Winter Conference on Applications of Computer Vision (WACV 2016)
Editors	Greg Mori, Robert Pless, Scott McCloskey, Rahul Sukthankar
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)	9781509006410
ISBN (Print)	9781509006427
DOIs	https://doi.org/10.1109/WACV.2016.7477700
Publication status	Published - 23 May 2016
Externally published	Yes
Event	IEEE Winter Conference on Applications of Computer Vision 2016 - Lake Placid, United States of America Duration: 7 Mar 2016 → 10 Mar 2016 http://www.wacv16.org/ http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=46372&copyownerid=26710 https://ieeexplore.ieee.org/xpl/conhome/7469250/proceeding (Proceedings)

Conference

Conference	IEEE Winter Conference on Applications of Computer Vision 2016
Abbreviated title	WACV 2016
Country/Territory	United States of America
City	Lake Placid
Period	7/03/16 → 10/03/16
Internet address	http://www.wacv16.org/ http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=46372&copyownerid=26710 https://ieeexplore.ieee.org/xpl/conhome/7469250/proceeding (Proceedings)

Access to Document

10.1109/WACV.2016.7477700

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] 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 = may,

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",

note = "IEEE Winter Conference on Applications of Computer Vision 2016, WACV 2016 ; Conference date: 07-03-2016 Through 10-03-2016",

url = "http://www.wacv16.org/, http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=46372&copyownerid=26710, https://ieeexplore.ieee.org/xpl/conhome/7469250/proceeding",

}

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, New York, 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 proceeding › Conference Paper › Research › peer-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

AN - SCOPUS:84977646599

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

T2 - IEEE Winter Conference on Applications of Computer Vision 2016

Y2 - 7 March 2016 through 10 March 2016

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

Fine-grained classification via mixture of deep convolutional neural networks

Abstract

Conference

Access to Document

Other files and links

Cite this