2022
DOI: 10.3390/rs15010108
|View full text |Cite
|
Sign up to set email alerts
|

NRN-RSSEG: A Deep Neural Network Model for Combating Label Noise in Semantic Segmentation of Remote Sensing Images

Abstract: The performance of deep neural networks depends on the accuracy of labeled samples, as they usually contain label noise. This study examines the semantic segmentation of remote sensing images that include label noise and proposes an anti-label-noise network framework, termed Labeled Noise Robust Network in Remote Sensing Image Semantic Segmentation (NRN-RSSEG), to combat label noise. The algorithm combines three main components: network, attention mechanism, and a noise-robust loss function. Three different no… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(6 citation statements)
references
References 35 publications
0
6
0
Order By: Relevance
“…Wang et al [49] introduced a novel cross-modal interactive fusion method to enhance the interactivity of modal fusion by combining multisource information, greatly improving classification accuracy. Xi et al [50] incorporated an anti-label-noise network framework into semantic segmentation, enhancing the model's robustness by mitigating label noise. However, to the best of our knowledge, scant attention has been directed toward investigating high dynamic range imaging of remote sensing images under arbitrary exposure conditions with noise.…”
Section: Remote Sensing Image Enhancementmentioning
confidence: 99%
“…Wang et al [49] introduced a novel cross-modal interactive fusion method to enhance the interactivity of modal fusion by combining multisource information, greatly improving classification accuracy. Xi et al [50] incorporated an anti-label-noise network framework into semantic segmentation, enhancing the model's robustness by mitigating label noise. However, to the best of our knowledge, scant attention has been directed toward investigating high dynamic range imaging of remote sensing images under arbitrary exposure conditions with noise.…”
Section: Remote Sensing Image Enhancementmentioning
confidence: 99%
“…Noise is a common feature of most datasets. As a result, research has been conducted into the handling of noise in all kinds of datasets and applications [48][49][50]. In this work, we explored the robustness of Feature Selection Algorithms through two kinds of noise: asymmetric label noise and irrelevant feature addition.…”
Section: Noise Resiliencementioning
confidence: 99%
“…(1) Specific network architecture [20,[22][23][24][44][45][46][47]. For synthetic aperture radar images, Ref.…”
Section: Deep Neural Network-based Label Noise Learning In Remote Sen...mentioning
confidence: 99%
“…To suppress the impact of label noise on the semantic segmentation of RS images, Ref. [47] constructed a general network framework by combining an attention mechanism and a noise robust loss function. (2) Robust loss function [19,20,25,[47][48][49][50].…”
Section: Deep Neural Network-based Label Noise Learning In Remote Sen...mentioning
confidence: 99%
See 1 more Smart Citation