Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments

Philipp Grüning; Amir Madany Mamlouk

doi:10.1109/IJCNN48605.2020.9207602

Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments

Abstract

CNNs are characterized in particular by the ability to independently learn suitable features from a given data set. However, the resulting latent space is optimized for the given training data. Especially for tasks that require a high generalization ability, like e.g. the segmentation of single cells in a microscopic image across various experiments, these specific solutions might not offer optimal results. In this work, we improve generalization with an additional unsupervised training step that operates in the latent space. First experiments with the Kaggle cell segmentation competition data show a strong improvement in the generalization of acquired knowledge when using a soft- and hard-competitive Neural-Gas algorithm for deep clustering with a standard CNN architecture.

Original language	English
Title of host publication	2020 International Joint Conference on Neural Networks (IJCNN)
Publisher	IEEE
Publication date	07.2020
Article number	9207602
ISBN (Print)	978-1-7281-6926-2
ISBN (Electronic)	978-1-7281-6927-9
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9207602
Publication status	Published - 07.2020
Event	2020 International Joint Conference on Neural Networks - Virtual, Glasgow, United Kingdom Duration: 19.07.2020 → 24.07.2020 Conference number: 163566

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Research Area: Intelligent Systems
Centers: Center for Artificial Intelligence Luebeck (ZKIL)

DFG Research Classification Scheme

4.43-05 Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing

Access to Document

10.1109/IJCNN48605.2020.9207602

Cite this

@inproceedings{9c151eb787f44d7889e6914c22b1ab0e,

title = "Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments",

abstract = "CNNs are characterized in particular by the ability to independently learn suitable features from a given data set. However, the resulting latent space is optimized for the given training data. Especially for tasks that require a high generalization ability, like e.g. the segmentation of single cells in a microscopic image across various experiments, these specific solutions might not offer optimal results. In this work, we improve generalization with an additional unsupervised training step that operates in the latent space. First experiments with the Kaggle cell segmentation competition data show a strong improvement in the generalization of acquired knowledge when using a soft- and hard-competitive Neural-Gas algorithm for deep clustering with a standard CNN architecture.",

author = "Philipp Gr{\"u}ning and Mamlouk, \{Amir Madany\}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

year = "2020",

month = jul,

doi = "10.1109/IJCNN48605.2020.9207602",

language = "English",

isbn = "978-1-7281-6926-2",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "IEEE",

booktitle = "2020 International Joint Conference on Neural Networks (IJCNN)",

}

Grüning, P & Mamlouk, AM 2020, Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments. in 2020 International Joint Conference on Neural Networks (IJCNN)., 9207602, Proceedings of the International Joint Conference on Neural Networks, IEEE, 2020 International Joint Conference on Neural Networks, Glasgow, United Kingdom, 19.07.20. https://doi.org/10.1109/IJCNN48605.2020.9207602

Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments. / Grüning, Philipp ; Mamlouk, Amir Madany.
2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020. 9207602 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments

AU - Grüning, Philipp

AU - Mamlouk, Amir Madany

N1 - Conference code: 163566

PY - 2020/7

Y1 - 2020/7

N2 - CNNs are characterized in particular by the ability to independently learn suitable features from a given data set. However, the resulting latent space is optimized for the given training data. Especially for tasks that require a high generalization ability, like e.g. the segmentation of single cells in a microscopic image across various experiments, these specific solutions might not offer optimal results. In this work, we improve generalization with an additional unsupervised training step that operates in the latent space. First experiments with the Kaggle cell segmentation competition data show a strong improvement in the generalization of acquired knowledge when using a soft- and hard-competitive Neural-Gas algorithm for deep clustering with a standard CNN architecture.

AB - CNNs are characterized in particular by the ability to independently learn suitable features from a given data set. However, the resulting latent space is optimized for the given training data. Especially for tasks that require a high generalization ability, like e.g. the segmentation of single cells in a microscopic image across various experiments, these specific solutions might not offer optimal results. In this work, we improve generalization with an additional unsupervised training step that operates in the latent space. First experiments with the Kaggle cell segmentation competition data show a strong improvement in the generalization of acquired knowledge when using a soft- and hard-competitive Neural-Gas algorithm for deep clustering with a standard CNN architecture.

UR - https://www.scopus.com/pages/publications/85093866888

U2 - 10.1109/IJCNN48605.2020.9207602

DO - 10.1109/IJCNN48605.2020.9207602

M3 - Conference contribution

SN - 978-1-7281-6926-2

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2020 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - 2020 International Joint Conference on Neural Networks

Y2 - 19 July 2020 through 24 July 2020

ER -

Deep Neural-Gas Clustering for Instance Segmentation across Imaging Experiments

Abstract

UN SDGs

Research Areas and Centers

DFG Research Classification Scheme

Access to Document

Other files and links

Fingerprint

Cite this