NSegment : Label-specific Deformations for Remote Sensing Image Segmentation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Yechan, Yoon, DongHo, Kim, SooYeon, Jeon, Moongu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908477532667904
author Kim, Yechan
Yoon, DongHo
Kim, SooYeon
Jeon, Moongu
author_facet Kim, Yechan
Yoon, DongHo
Kim, SooYeon
Jeon, Moongu
contents Labeling errors in remote sensing (RS) image segmentation datasets often remain implicit and subtle due to ambiguous class boundaries, mixed pixels, shadows, complex terrain features, and subjective annotator bias. Furthermore, the scarcity of annotated RS data due to the high cost of labeling complicates training noise-robust models. While sophisticated mechanisms such as label selection or noise correction might address the issue mentioned above, they tend to increase training time and add implementation complexity. In this paper, we propose NSegment-a simple yet effective data augmentation solution to mitigate this issue. Unlike traditional methods, it applies elastic transformations only to segmentation labels, varying deformation intensity per sample in each training epoch to address annotation inconsistencies. Experimental results demonstrate that our approach improves the performance of RS image segmentation over various state-of-the-art models.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19634
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NSegment : Label-specific Deformations for Remote Sensing Image Segmentation
Kim, Yechan
Yoon, DongHo
Kim, SooYeon
Jeon, Moongu
Computer Vision and Pattern Recognition
Labeling errors in remote sensing (RS) image segmentation datasets often remain implicit and subtle due to ambiguous class boundaries, mixed pixels, shadows, complex terrain features, and subjective annotator bias. Furthermore, the scarcity of annotated RS data due to the high cost of labeling complicates training noise-robust models. While sophisticated mechanisms such as label selection or noise correction might address the issue mentioned above, they tend to increase training time and add implementation complexity. In this paper, we propose NSegment-a simple yet effective data augmentation solution to mitigate this issue. Unlike traditional methods, it applies elastic transformations only to segmentation labels, varying deformation intensity per sample in each training epoch to address annotation inconsistencies. Experimental results demonstrate that our approach improves the performance of RS image segmentation over various state-of-the-art models.
title NSegment : Label-specific Deformations for Remote Sensing Image Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.19634