Saved in:
Bibliographic Details
Main Authors: Elwaradi, Reda, Gimenez, Julien, Hordoir, Stéphane, Hamma, Mehdi Ait, Chan-Hon-Tong, Adrien, Weissgerber, Flora
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.13573
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915861990735872
author Elwaradi, Reda
Gimenez, Julien
Hordoir, Stéphane
Hamma, Mehdi Ait
Chan-Hon-Tong, Adrien
Weissgerber, Flora
author_facet Elwaradi, Reda
Gimenez, Julien
Hordoir, Stéphane
Hamma, Mehdi Ait
Chan-Hon-Tong, Adrien
Weissgerber, Flora
contents High-resolution sea ice mapping using Synthetic Aperture Radar (SAR) is crucial for Arctic navigation and climate monitoring. However, operational ice charts provide only coarse, region-level polygons (weak labels), forcing automated segmentation models to struggle with pixel-level accuracy and often yielding under-confident, blurred concentration maps. In this paper, we propose a weakly supervised deep learning pipeline that fuses Sentinel-1 SAR and AMSR-2 radiometry data using a U-Net architecture trained with a region-based loss. To overcome the severe under-confidence caused by weak labels, we introduce an Analytical Logit Scaling method applied post-inference. By dynamically calculating the temperature and bias based on the latent space percentiles (2\% and 98\%) of each scene, we force a physical binarization of the predictions. This adaptive scaling acts as a topological extractor, successfully revealing fine-grained sea ice fractures (leads) at a 40-meter resolution without requiring any manual pixel-level annotations. Our approach not only resolves local topology but also perfectly preserves regional macroscopic concentrations, achieving a 78\% accuracy on highly fragmented summer scenes, thereby bridging the gap between weakly supervised learning and high-resolution physical segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13573
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Analytical Logit Scaling for High-Resolution Sea Ice Topology Retrieval from Weakly Labeled SAR Imagery
Elwaradi, Reda
Gimenez, Julien
Hordoir, Stéphane
Hamma, Mehdi Ait
Chan-Hon-Tong, Adrien
Weissgerber, Flora
Computer Vision and Pattern Recognition
High-resolution sea ice mapping using Synthetic Aperture Radar (SAR) is crucial for Arctic navigation and climate monitoring. However, operational ice charts provide only coarse, region-level polygons (weak labels), forcing automated segmentation models to struggle with pixel-level accuracy and often yielding under-confident, blurred concentration maps. In this paper, we propose a weakly supervised deep learning pipeline that fuses Sentinel-1 SAR and AMSR-2 radiometry data using a U-Net architecture trained with a region-based loss. To overcome the severe under-confidence caused by weak labels, we introduce an Analytical Logit Scaling method applied post-inference. By dynamically calculating the temperature and bias based on the latent space percentiles (2\% and 98\%) of each scene, we force a physical binarization of the predictions. This adaptive scaling acts as a topological extractor, successfully revealing fine-grained sea ice fractures (leads) at a 40-meter resolution without requiring any manual pixel-level annotations. Our approach not only resolves local topology but also perfectly preserves regional macroscopic concentrations, achieving a 78\% accuracy on highly fragmented summer scenes, thereby bridging the gap between weakly supervised learning and high-resolution physical segmentation.
title Analytical Logit Scaling for High-Resolution Sea Ice Topology Retrieval from Weakly Labeled SAR Imagery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13573