Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ...
Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics perf...
Main Authors: | , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2310.17135 https://arxiv.org/abs/2310.17135 |
id |
ftdatacite:10.48550/arxiv.2310.17135 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2310.17135 2023-12-03T10:30:05+01:00 Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... de Lima, Rafael Pires Vahedi, Behzad Karimzadeh, Morteza 2023 https://dx.doi.org/10.48550/arxiv.2310.17135 https://arxiv.org/abs/2310.17135 unknown arXiv https://dx.doi.org/10.1109/igarss52108.2023.10282060 Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering ScholarlyArticle Text article-journal Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2310.1713510.1109/igarss52108.2023.10282060 2023-11-03T11:11:09Z Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics performance not always translate to adequate outputs. Sea ice type classes are imbalanced, requiring special treatment during training. We evaluate how three different loss functions, some developed for imbalanced class problems, affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent. ... Article in Journal/Newspaper Sea ice DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering de Lima, Rafael Pires Vahedi, Behzad Karimzadeh, Morteza Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
description |
Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics performance not always translate to adequate outputs. Sea ice type classes are imbalanced, requiring special treatment during training. We evaluate how three different loss functions, some developed for imbalanced class problems, affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent. ... |
format |
Article in Journal/Newspaper |
author |
de Lima, Rafael Pires Vahedi, Behzad Karimzadeh, Morteza |
author_facet |
de Lima, Rafael Pires Vahedi, Behzad Karimzadeh, Morteza |
author_sort |
de Lima, Rafael Pires |
title |
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
title_short |
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
title_full |
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
title_fullStr |
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
title_full_unstemmed |
Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation ... |
title_sort |
comparison of cross-entropy, dice, and focal loss for sea ice type segmentation ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2310.17135 https://arxiv.org/abs/2310.17135 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
https://dx.doi.org/10.1109/igarss52108.2023.10282060 |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2310.1713510.1109/igarss52108.2023.10282060 |
_version_ |
1784255757700562944 |