GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data

Konstantin A. Maslov; Claudio Persello; Thomas Schellenberger; Alfred Stein

doi:10.1109/IGARSS52108.2023.10281828

GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data

Konstantin A. Maslov^*, Claudio Persello, Thomas Schellenberger, Alfred Stein

^*Corresponding author for this work

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

34 Downloads (Pure)

Abstract

Glacier mapping is essential for studying and monitoring the impacts of climate change. However, several challenges such as debris-covered ice and highly variable landscapes across glacierized regions worldwide complicate large-scale glacier mapping in a fully-automated manner. This work presents a novel hybrid CNN-transformer model (GlaViTU) for multi-regional glacier mapping. Our model outperforms three baseline models - SETR-B/16, ResU-Net and TransU-Net - achieving a higher mean IoU of 0.875 and demonstrates better generalization ability. The proposed model is also parameter-efficient, with approximately 10 and 3 times fewer parameters than SETR-B/16 and ResU-Net, respectively. Our results provide a solid foundation for future studies on the application of deep learning methods for global glacier mapping. To facilitate reproducibility, we have shared our data set, codebase and pretrained models on GitHub at https://github.com/konstantin-a-maslov/GlaViTU-IGARSS2023.

Original language	English
Title of host publication	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	IEEE
Pages	1233-1236
Number of pages	4
ISBN (Electronic)	9798350320107
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10281828
Publication status	Published - 2023
Event	43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena Convention Center, Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023 Conference number: 43 https://2023.ieeeigarss.org/index.php

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2023-July

Conference

Conference	43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Abbreviated title	IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23
Internet address	https://2023.ieeeigarss.org/index.php

Keywords

convolutional neural network
deep learning
Glacier mapping
vision transformer
2024 OA procedure

Access to Document

10.1109/IGARSS52108.2023.10281828

GLAVITU_A_Hybrid_CNN-Transformer_for_Multi-Regional_Glacier_Mapping_from_Multi-Source_DataFinal published version, 8.82 MBLicence: Taverne

Cite this

Maslov, K. A., Persello, C., Schellenberger, T., & Stein, A. (2023). GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 1233-1236). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July). IEEE. https://doi.org/10.1109/IGARSS52108.2023.10281828

@inproceedings{d1440b6c214b49aeb9eace94e74b3355,

title = "GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data",

abstract = "Glacier mapping is essential for studying and monitoring the impacts of climate change. However, several challenges such as debris-covered ice and highly variable landscapes across glacierized regions worldwide complicate large-scale glacier mapping in a fully-automated manner. This work presents a novel hybrid CNN-transformer model (GlaViTU) for multi-regional glacier mapping. Our model outperforms three baseline models - SETR-B/16, ResU-Net and TransU-Net - achieving a higher mean IoU of 0.875 and demonstrates better generalization ability. The proposed model is also parameter-efficient, with approximately 10 and 3 times fewer parameters than SETR-B/16 and ResU-Net, respectively. Our results provide a solid foundation for future studies on the application of deep learning methods for global glacier mapping. To facilitate reproducibility, we have shared our data set, codebase and pretrained models on GitHub at https://github.com/konstantin-a-maslov/GlaViTU-IGARSS2023.",

keywords = "convolutional neural network, deep learning, Glacier mapping, vision transformer, 2024 OA procedure",

author = "Maslov, {Konstantin A.} and Claudio Persello and Thomas Schellenberger and Alfred Stein",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10281828",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "IEEE",

pages = "1233--1236",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

address = "United States",

url = "https://2023.ieeeigarss.org/index.php",

}

Maslov, KA , Persello, C, Schellenberger, T & Stein, A 2023, GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2023-July, IEEE, pp. 1233-1236, 43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, California, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10281828

GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data. / Maslov, Konstantin A.; Persello, Claudio; Schellenberger, Thomas et al.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. IEEE, 2023. p. 1233-1236 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July).

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

TY - GEN

T1 - GLAVITU

T2 - 43rd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

AU - Maslov, Konstantin A.

AU - Persello, Claudio

AU - Schellenberger, Thomas

AU - Stein, Alfred

N1 - Conference code: 43

PY - 2023

Y1 - 2023

N2 - Glacier mapping is essential for studying and monitoring the impacts of climate change. However, several challenges such as debris-covered ice and highly variable landscapes across glacierized regions worldwide complicate large-scale glacier mapping in a fully-automated manner. This work presents a novel hybrid CNN-transformer model (GlaViTU) for multi-regional glacier mapping. Our model outperforms three baseline models - SETR-B/16, ResU-Net and TransU-Net - achieving a higher mean IoU of 0.875 and demonstrates better generalization ability. The proposed model is also parameter-efficient, with approximately 10 and 3 times fewer parameters than SETR-B/16 and ResU-Net, respectively. Our results provide a solid foundation for future studies on the application of deep learning methods for global glacier mapping. To facilitate reproducibility, we have shared our data set, codebase and pretrained models on GitHub at https://github.com/konstantin-a-maslov/GlaViTU-IGARSS2023.

AB - Glacier mapping is essential for studying and monitoring the impacts of climate change. However, several challenges such as debris-covered ice and highly variable landscapes across glacierized regions worldwide complicate large-scale glacier mapping in a fully-automated manner. This work presents a novel hybrid CNN-transformer model (GlaViTU) for multi-regional glacier mapping. Our model outperforms three baseline models - SETR-B/16, ResU-Net and TransU-Net - achieving a higher mean IoU of 0.875 and demonstrates better generalization ability. The proposed model is also parameter-efficient, with approximately 10 and 3 times fewer parameters than SETR-B/16 and ResU-Net, respectively. Our results provide a solid foundation for future studies on the application of deep learning methods for global glacier mapping. To facilitate reproducibility, we have shared our data set, codebase and pretrained models on GitHub at https://github.com/konstantin-a-maslov/GlaViTU-IGARSS2023.

KW - convolutional neural network

KW - deep learning

KW - Glacier mapping

KW - vision transformer

KW - 2024 OA procedure

U2 - 10.1109/IGARSS52108.2023.10281828

DO - 10.1109/IGARSS52108.2023.10281828

M3 - Conference contribution

AN - SCOPUS:85178335951

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1233

EP - 1236

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - IEEE

Y2 - 16 July 2023 through 21 July 2023

ER -

GLAVITU: A Hybrid CNN-Transformer for Multi-Regional Glacier Mapping from Multi-Source Data

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this