Learning from Noisy Pseudo-labels for All-Weather Land Cover Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Wang, Wang, Zhiyu, Guo, Xin, Duan, Puhong, Kang, Xudong, Li, Shutao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908325759680512
author Liu, Wang
Wang, Zhiyu
Guo, Xin
Duan, Puhong
Kang, Xudong
Li, Shutao
author_facet Liu, Wang
Wang, Zhiyu
Guo, Xin
Duan, Puhong
Kang, Xudong
Li, Shutao
contents Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by significant speckle noise, rendering the annotation or segmentation of SAR images a formidable task. Recent efforts have resorted to annotating paired optical-SAR images to generate pseudo-labels through the utilization of an optical image segmentation network. However, these pseudo-labels are laden with noise, leading to suboptimal performance in SAR image segmentation. In this study, we introduce a more precise method for generating pseudo-labels by incorporating semi-supervised learning alongside a novel image resolution alignment augmentation. Furthermore, we introduce a symmetric cross-entropy loss to mitigate the impact of noisy pseudo-labels. Additionally, a bag of training and testing tricks is utilized to generate better land-cover mapping results. Our experiments on the GRSS data fusion contest indicate the effectiveness of the proposed method, which achieves first place. The code is available at https://github.com/StuLiu/DFC2025Track1.git.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13458
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning from Noisy Pseudo-labels for All-Weather Land Cover Mapping
Liu, Wang
Wang, Zhiyu
Guo, Xin
Duan, Puhong
Kang, Xudong
Li, Shutao
Computer Vision and Pattern Recognition
Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by significant speckle noise, rendering the annotation or segmentation of SAR images a formidable task. Recent efforts have resorted to annotating paired optical-SAR images to generate pseudo-labels through the utilization of an optical image segmentation network. However, these pseudo-labels are laden with noise, leading to suboptimal performance in SAR image segmentation. In this study, we introduce a more precise method for generating pseudo-labels by incorporating semi-supervised learning alongside a novel image resolution alignment augmentation. Furthermore, we introduce a symmetric cross-entropy loss to mitigate the impact of noisy pseudo-labels. Additionally, a bag of training and testing tricks is utilized to generate better land-cover mapping results. Our experiments on the GRSS data fusion contest indicate the effectiveness of the proposed method, which achieves first place. The code is available at https://github.com/StuLiu/DFC2025Track1.git.
title Learning from Noisy Pseudo-labels for All-Weather Land Cover Mapping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.13458