Feature learning via mixtures of DCNNs for fine-grained plant classification

Chris McCool; ZongYuan Ge; Peter Corke

Feature learning via mixtures of DCNNs for fine-grained plant classification

Chris McCool, ZongYuan Ge, Peter Corke

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

We present the plant classification system submitted by the QUT RV team to the LifeCLEF 2016 plant task. Our system learns two deep convolutional neural network models. The first is a domain-specific model and the second is a mixture of content specific models, one for each of the plant organs such as branch, leaf, fruit, ower and stem. We combine these two models and experiments on the PlantCLEF2016 dataset show that this approach provides an improvement over the baseline system with the mean average precision improving from 0:603 to 0:629 on the test set.

Original language	English
Title of host publication	CLEF 2016
Subtitle of host publication	CLEF2016 Working Notes
Editors	Krisztian Balog, Linda Cappellato, Nicola Ferro, Craig Macdonald
Place of Publication	Aachen Germany
Publisher	RWTH Aachen University
Pages	511-517
Number of pages	7
Volume	1609
Publication status	Published - 1 Jan 2016
Externally published	Yes
Event	Conference and Labs of the Evaluation Forum 2016: Information Access Evaluation meets Multilinguality, Multimodality and Interaction - University of Évora, Evora, Portugal Duration: 5 Sep 2016 → 8 Sep 2016 Conference number: 7th http://clef2016.clef-initiative.eu/index.php

Publication series

Name	CEUR Workshop Proceedings
Publisher	Rheinisch-Westfaelische Technische Hochschule Aachen * Lehrstuhl Informatik V
ISSN (Print)	1613-0073

Conference

Conference	Conference and Labs of the Evaluation Forum 2016
Abbreviated title	CLEF 2016
Country	Portugal
City	Evora
Period	5/09/16 → 8/09/16
Internet address	http://clef2016.clef-initiative.eu/index.php

Keywords

Deep Convolutional Neural Network
Mixture Of Deep Convolutional Neural Networks
Plant Classification

Access to Document

251382280-oaFinal published version, 1.31 MB

Cite this

@inproceedings{fcf023fbf98b42db91856476d6d769d9,

title = "Feature learning via mixtures of DCNNs for fine-grained plant classification",

abstract = "We present the plant classification system submitted by the QUT RV team to the LifeCLEF 2016 plant task. Our system learns two deep convolutional neural network models. The first is a domain-specific model and the second is a mixture of content specific models, one for each of the plant organs such as branch, leaf, fruit, ower and stem. We combine these two models and experiments on the PlantCLEF2016 dataset show that this approach provides an improvement over the baseline system with the mean average precision improving from 0:603 to 0:629 on the test set.",

keywords = "Deep Convolutional Neural Network, Mixture Of Deep Convolutional Neural Networks, Plant Classification",

author = "Chris McCool and ZongYuan Ge and Peter Corke",

year = "2016",

month = jan,

day = "1",

language = "English",

volume = "1609",

series = "CEUR Workshop Proceedings",

publisher = "RWTH Aachen University",

pages = "511--517",

editor = "Krisztian Balog and Linda Cappellato and Nicola Ferro and Craig Macdonald",

booktitle = "CLEF 2016",

note = " Conference and Labs of the Evaluation Forum 2016 : Information Access Evaluation meets Multilinguality, Multimodality and Interaction, CLEF 2016 ; Conference date: 05-09-2016 Through 08-09-2016",

url = "http://clef2016.clef-initiative.eu/index.php",

}

McCool, C, Ge, Z & Corke, P 2016, Feature learning via mixtures of DCNNs for fine-grained plant classification. in K Balog, L Cappellato, N Ferro & C Macdonald (eds), CLEF 2016: CLEF2016 Working Notes. vol. 1609, CEUR Workshop Proceedings, RWTH Aachen University, Aachen Germany, pp. 511-517, Conference and Labs of the Evaluation Forum 2016, Evora, Portugal, 5/09/16. <http://ceur-ws.org/Vol-1609/16090511.pdf>

Feature learning via mixtures of DCNNs for fine-grained plant classification. / McCool, Chris; Ge, ZongYuan; Corke, Peter.

CLEF 2016: CLEF2016 Working Notes. ed. / Krisztian Balog; Linda Cappellato; Nicola Ferro; Craig Macdonald. Vol. 1609 Aachen Germany : RWTH Aachen University, 2016. p. 511-517 (CEUR Workshop Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Feature learning via mixtures of DCNNs for fine-grained plant classification

AU - McCool, Chris

AU - Ge, ZongYuan

AU - Corke, Peter

N1 - Conference code: 7th

PY - 2016/1/1

Y1 - 2016/1/1

N2 - We present the plant classification system submitted by the QUT RV team to the LifeCLEF 2016 plant task. Our system learns two deep convolutional neural network models. The first is a domain-specific model and the second is a mixture of content specific models, one for each of the plant organs such as branch, leaf, fruit, ower and stem. We combine these two models and experiments on the PlantCLEF2016 dataset show that this approach provides an improvement over the baseline system with the mean average precision improving from 0:603 to 0:629 on the test set.

AB - We present the plant classification system submitted by the QUT RV team to the LifeCLEF 2016 plant task. Our system learns two deep convolutional neural network models. The first is a domain-specific model and the second is a mixture of content specific models, one for each of the plant organs such as branch, leaf, fruit, ower and stem. We combine these two models and experiments on the PlantCLEF2016 dataset show that this approach provides an improvement over the baseline system with the mean average precision improving from 0:603 to 0:629 on the test set.

KW - Deep Convolutional Neural Network

KW - Mixture Of Deep Convolutional Neural Networks

KW - Plant Classification

UR - http://www.scopus.com/inward/record.url?scp=85019582545&partnerID=8YFLogxK

M3 - Conference Paper

AN - SCOPUS:85019582545

VL - 1609

T3 - CEUR Workshop Proceedings

SP - 511

EP - 517

BT - CLEF 2016

A2 - Balog, Krisztian

A2 - Cappellato, Linda

A2 - Ferro, Nicola

A2 - Macdonald, Craig

PB - RWTH Aachen University

CY - Aachen Germany

T2 - Conference and Labs of the Evaluation Forum 2016

Y2 - 5 September 2016 through 8 September 2016

ER -