A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images

Wang, Libo; Li, Rui; Duan, Chenxi; Zhang, Ce ORCID: https://orcid.org/0000-0001-5100-3584; Meng, Xiaoliang; Fang, Shenghui. 2022 A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geoscience and Remote Sensing Letters, 19, 6506105. 5, pp. https://doi.org/10.1109/LGRS.2022.3143368

Full text not available from this repository.

Abstract/Summary

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	https://doi.org/10.1109/LGRS.2022.3143368
UKCEH and CEH Sections/Science Areas:	Soils and Land Use (Science Area 2017-)
ISSN:	1545-598X
Additional Keywords:	transformers, semantics, image segmentation, feature extraction, remote sensing, decoding, standards, fine-resolution remote sensing images, semantic segmentation
NORA Subject Terms:	Earth Sciences Electronics, Engineering and Technology Data and Information
Date made live:	30 Mar 2022 11:47 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/532365

Actions (login required)

View Item

Document Downloads

More statistics for this item...