Coral classification using densenet and cross-modality transfer learning

Lian Xu; Mohammed Bennamoun; Farid Boussaid; Senjian An; Ferdous Sohel

doi:10.1109/IJCNN.2019.8852235

Coral classification using densenet and cross-modality transfer learning

Lian Xu, Mohammed Bennamoun, Farid Boussaid, Senjian An, Ferdous Sohel

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

5 Citations (Scopus)

Abstract

Coral classification is a challenging task due to the complex morphology and ambiguous boundaries of corals. This paper investigates the benefits of Densely connected convolutional network (DenseNet) and multi-modal image translation techniques in boosting image classification performance by synthesizing missing fluorescence information. To this end, an imageconditional Generative Adversarial Network (GAN) based image translator is trained to model the relationship between reflectance and fluorescence images. Through this image translator, fluorescence images can be generated from the available reflectance images to provide complementary information. During the classification phase, reflectance and translated fluorescence images are combined to obtain more discriminative representations and produce improved classification performance. We present results on the EFC and MLC datasets and report state-of-the-art coral classification performance. © 2019 IEEE.

Original language	English
Title of host publication	International Joint Conference on Neural Networks (IJCNN)
Place of Publication	USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1-8
Number of pages	8
ISBN (Electronic)	9781728119854
ISBN (Print)	978-172811985-4
DOIs	https://doi.org/10.1109/IJCNN.2019.8852235
Publication status	Published - Jul 2019
Event	International Joint Conference on Neural Networks - InterContinental Budapest Hotel, Budapest, Hungary Duration: 14 Jul 2019 → 19 Jul 2019 https://www.ijcnn.org/

Conference

Conference	International Joint Conference on Neural Networks
Abbreviated title	IJCNN 2019
Country/Territory	Hungary
City	Budapest
Period	14/07/19 → 19/07/19
Other	The 2019 International Joint Conference on Neural Networks (IJCNN) will be held at the InterContinental Budapest Hotel in Budapest, Hungary on July 14-19, 2019. The conference is organized by the International Neural Network Society (INNS) in cooperation with the IEEE Computational Intelligence Society, and is the premier international meeting for researchers and other professionals in neural networks and related areas. It will feature invited plenary talks by world-renowned speakers in the areas of neural network theory and applications, computational neuroscience, robotics, and distrbuted intelligence. In addition to regular technical sessions with oral and poster presentations, the conference program will include special sessions, competitions, tutorials and workshops on topics of current interest.
Internet address	https://www.ijcnn.org/

Access to Document

10.1109/IJCNN.2019.8852235

Cite this

@inproceedings{7a307ecb4b1042c880b35b68a5e3c7f1,

title = "Coral classification using densenet and cross-modality transfer learning",

abstract = "Coral classification is a challenging task due to the complex morphology and ambiguous boundaries of corals. This paper investigates the benefits of Densely connected convolutional network (DenseNet) and multi-modal image translation techniques in boosting image classification performance by synthesizing missing fluorescence information. To this end, an imageconditional Generative Adversarial Network (GAN) based image translator is trained to model the relationship between reflectance and fluorescence images. Through this image translator, fluorescence images can be generated from the available reflectance images to provide complementary information. During the classification phase, reflectance and translated fluorescence images are combined to obtain more discriminative representations and produce improved classification performance. We present results on the EFC and MLC datasets and report state-of-the-art coral classification performance. {\textcopyright} 2019 IEEE.",

keywords = "Deep learing, Convolutional neural network, Multi-modal image translation, Transfer learning, coral classification",

author = "Lian Xu and Mohammed Bennamoun and Farid Boussaid and Senjian An and Ferdous Sohel",

year = "2019",

month = jul,

doi = "10.1109/IJCNN.2019.8852235",

language = "English",

isbn = "978-172811985-4",

pages = "1--8",

booktitle = "International Joint Conference on Neural Networks (IJCNN)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "International Joint Conference on Neural Networks, IJCNN 2019 ; Conference date: 14-07-2019 Through 19-07-2019",

url = "https://www.ijcnn.org/",

}

Xu, L , Bennamoun, M , Boussaid, F, An, S & Sohel, F 2019, Coral classification using densenet and cross-modality transfer learning. in International Joint Conference on Neural Networks (IJCNN) ., 8852235, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 1-8, International Joint Conference on Neural Networks, Budapest, Hungary, 14/07/19. https://doi.org/10.1109/IJCNN.2019.8852235

TY - GEN

T1 - Coral classification using densenet and cross-modality transfer learning

AU - Xu, Lian

AU - Bennamoun, Mohammed

AU - Boussaid, Farid

AU - An, Senjian

AU - Sohel, Ferdous

PY - 2019/7

Y1 - 2019/7

N2 - Coral classification is a challenging task due to the complex morphology and ambiguous boundaries of corals. This paper investigates the benefits of Densely connected convolutional network (DenseNet) and multi-modal image translation techniques in boosting image classification performance by synthesizing missing fluorescence information. To this end, an imageconditional Generative Adversarial Network (GAN) based image translator is trained to model the relationship between reflectance and fluorescence images. Through this image translator, fluorescence images can be generated from the available reflectance images to provide complementary information. During the classification phase, reflectance and translated fluorescence images are combined to obtain more discriminative representations and produce improved classification performance. We present results on the EFC and MLC datasets and report state-of-the-art coral classification performance. © 2019 IEEE.

AB - Coral classification is a challenging task due to the complex morphology and ambiguous boundaries of corals. This paper investigates the benefits of Densely connected convolutional network (DenseNet) and multi-modal image translation techniques in boosting image classification performance by synthesizing missing fluorescence information. To this end, an imageconditional Generative Adversarial Network (GAN) based image translator is trained to model the relationship between reflectance and fluorescence images. Through this image translator, fluorescence images can be generated from the available reflectance images to provide complementary information. During the classification phase, reflectance and translated fluorescence images are combined to obtain more discriminative representations and produce improved classification performance. We present results on the EFC and MLC datasets and report state-of-the-art coral classification performance. © 2019 IEEE.

KW - Deep learing

KW - Convolutional neural network

KW - Multi-modal image translation

KW - Transfer learning

KW - coral classification

UR - https://www.ijcnn.org/

UR - https://www.ijcnn.org/final-paper-submissions

UR - http://www.scopus.com/inward/record.url?scp=85073236693&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2019.8852235

DO - 10.1109/IJCNN.2019.8852235

M3 - Conference paper

SN - 978-172811985-4

SP - 1

EP - 8

BT - International Joint Conference on Neural Networks (IJCNN)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

T2 - International Joint Conference on Neural Networks

Y2 - 14 July 2019 through 19 July 2019

ER -

Coral classification using densenet and cross-modality transfer learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Advanced Computer Vision Techniques for Marine Ecology

Revocable 2D/3D Shape Based Multimodal Hand Biometrics for Personal Identification & Verification

Cite this

Coral classification using densenet and cross-modality transfer learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Projects

Advanced Computer Vision Techniques for Marine Ecology

Revocable 2D/3D Shape Based Multimodal Hand Biometrics for Personal Identification & Verification

Cite this