Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ...
Fully supervised deep learning approaches have demonstrated impressive accuracy in sea ice classification, but their dependence on high-resolution labels presents a significant challenge due to the difficulty of obtaining such data. In response, our weakly supervised learning method provides a compe...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2024
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2405.10456 https://arxiv.org/abs/2405.10456 |
id |
ftdatacite:10.48550/arxiv.2405.10456 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2405.10456 2024-09-09T20:06:50+00:00 Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... Patel, Muhammed Chen, Xinwei Xu, Linlin Chen, Yuhao Scott, K Andrea Clausi, David A. 2024 https://dx.doi.org/10.48550/arxiv.2405.10456 https://arxiv.org/abs/2405.10456 unknown arXiv 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 FOS Computer and information sciences Article article Preprint CreativeWork 2024 ftdatacite https://doi.org/10.48550/arxiv.2405.10456 2024-06-17T10:04:27Z Fully supervised deep learning approaches have demonstrated impressive accuracy in sea ice classification, but their dependence on high-resolution labels presents a significant challenge due to the difficulty of obtaining such data. In response, our weakly supervised learning method provides a compelling alternative by utilizing lower-resolution regional labels from expert-annotated ice charts. This approach achieves exceptional pixel-level classification performance by introducing regional loss representations during training to measure the disparity between predicted and ice chart-derived sea ice type distributions. Leveraging the AI4Arctic Sea Ice Challenge Dataset, our method outperforms the fully supervised U-Net benchmark, the top solution of the AutoIce challenge, in both mapping resolution and class-wise accuracy, marking a significant advancement in automated operational sea ice mapping. ... : Published at ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop ... Article in Journal/Newspaper Sea ice DataCite |
institution |
Open Polar |
collection |
DataCite |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences Patel, Muhammed Chen, Xinwei Xu, Linlin Chen, Yuhao Scott, K Andrea Clausi, David A. Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV FOS Computer and information sciences |
description |
Fully supervised deep learning approaches have demonstrated impressive accuracy in sea ice classification, but their dependence on high-resolution labels presents a significant challenge due to the difficulty of obtaining such data. In response, our weakly supervised learning method provides a compelling alternative by utilizing lower-resolution regional labels from expert-annotated ice charts. This approach achieves exceptional pixel-level classification performance by introducing regional loss representations during training to measure the disparity between predicted and ice chart-derived sea ice type distributions. Leveraging the AI4Arctic Sea Ice Challenge Dataset, our method outperforms the fully supervised U-Net benchmark, the top solution of the AutoIce challenge, in both mapping resolution and class-wise accuracy, marking a significant advancement in automated operational sea ice mapping. ... : Published at ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop ... |
format |
Article in Journal/Newspaper |
author |
Patel, Muhammed Chen, Xinwei Xu, Linlin Chen, Yuhao Scott, K Andrea Clausi, David A. |
author_facet |
Patel, Muhammed Chen, Xinwei Xu, Linlin Chen, Yuhao Scott, K Andrea Clausi, David A. |
author_sort |
Patel, Muhammed |
title |
Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
title_short |
Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
title_full |
Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
title_fullStr |
Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
title_full_unstemmed |
Region-level labels in ice charts can produce pixel-level segmentation for Sea Ice types ... |
title_sort |
region-level labels in ice charts can produce pixel-level segmentation for sea ice types ... |
publisher |
arXiv |
publishDate |
2024 |
url |
https://dx.doi.org/10.48550/arxiv.2405.10456 https://arxiv.org/abs/2405.10456 |
genre |
Sea ice |
genre_facet |
Sea ice |
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.2405.10456 |
_version_ |
1809939408815652864 |