Dual Lightweight Network with Attention and Feature Fusion for Semantic Segmentation of High-Resolution Remote Sensing Images

Zhang, Yijie; Chen, Yulan; Ma, Qijun; He, Changtao; Cheng, Jian

doi:10.1109/igarss47720.2021.9553680

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation assigns category labels to each pixel of an image, which is a fundamental task in computer vision (CV). 16 In 2012, AlexNet 17 won the ImageNet Image Competition, triggering an upsurge of research in deep neural networks. 18 Since then, researchers have developed many constructive networks and achieved extremely high performance on various downstream tasks in CV.…”

Section: Semantic Segmentation Based On Cnnmentioning

confidence: 99%

See 1 more Smart Citation

SN-Unetformer: a dual encoder hybrid architecture for complex targets in high-resolution remote sensing images

Zhu

Peng

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Accurately identifying the semantic information of complex objects is a challenging problem in semantic segmentation of remote sensing images. We propose a bi-encoder network for semantic segmentation of complex targets, called the SN-Unetformer. It combines ConvNeXt and Swin Transformer into a bi-encoder and constructs a feature fusion module (FFM) to fully integrate the semantic information of the bi-encoder by exploiting channel dependence. Moreover, an efficient attention mechanism has been introduced to model the global-local relationship. To the best of our knowledge, our proposed network is innovative, as it is the first method to combine two popular networks, ConvNeXt and the Swin Transformer, into a dual encoder. Our SN-Unetformer has been tested on large-scale Vaihingen and Potsdam datasets, as well as the LoveDA dataset, with significant challenges. Compared to current advanced methods for semantic segmentation for remote sensing images, our accuracy is significantly better. In particular, our method achieves 84.3% of mean intersection over union on the Vaihingen dataset, which is the best result currently available for this dataset.

show abstract

Section: Semantic Segmentation Based On Cnnmentioning

confidence: 99%

“…Semantic segmentation assigns category labels to each pixel of an image, which is a fundamental task in computer vision (CV) 16 …”

Section: Related Workmentioning

confidence: 99%

SN-Unetformer: a dual encoder hybrid architecture for complex targets in high-resolution remote sensing images

Zhu

Peng

et al. 2023

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

Multilevel Feature Fusion and Attention Network for High-Resolution Remote Sensing Image Semantic Labeling

Zhang

Cheng

Bai

et al. 2022

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Lightweight Attention Network for Very High-Resolution Image Semantic Segmentation

Guan

Wang

Bruzzone

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Dual Lightweight Network with Attention and Feature Fusion for Semantic Segmentation of High-Resolution Remote Sensing Images

Cited by 4 publications

References 9 publications

SN-Unetformer: a dual encoder hybrid architecture for complex targets in high-resolution remote sensing images

SN-Unetformer: a dual encoder hybrid architecture for complex targets in high-resolution remote sensing images

Multilevel Feature Fusion and Attention Network for High-Resolution Remote Sensing Image Semantic Labeling

Lightweight Attention Network for Very High-Resolution Image Semantic Segmentation

Contact Info

Product

Resources

About