DSM-Assisted Unsupervised Domain Adaptive Network for Semantic Segmentation of Remote Sensing Imagery

Zhou, Shunping; Feng, Yuting; Li, Shengwen; Zheng, Daoyuan; Fang, Fang; Liu, Yuanyuan; Wan, Bo

doi:10.1109/tgrs.2023.3268362

Cited by 7 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A DSM provides elevation data of objects in a remote sensing image, facilitating the segmentation of tall objects, such as buildings and trees. Utilizing DSMs to extract additional features can further improve the semantic segmentation of multispectral images [228], [229], [232], [248], [233], [235], [236], [238]. In addition, other indicators such as Normalized DSM(NDSM) [230], [231], Digital Elevation Model (DEM) [123], [227], [237], Normalized Difference Vegetation Index (NDVI) [230], [231], [234] from the near-infrared and red channels, Normalized Difference Water Index [231] using near-infrared and green channels, are utilized to fuse with the multispectral images.…”

Section: ) What To Fusementioning

confidence: 99%

“…Therefore, it is better to select complementary information for fusion adaptively. Among them, the most representative strategies include attention mechanism [236], [238], [242], [243], [244], gate mechanism [234], [235], [238], [245], Graph neural network (GCN) [246], GAN [247], conditional random field [239].…”

Section: Fusion Of Multispectral Image and Lidar Datamentioning

confidence: 99%

See 1 more Smart Citation

Deep-Learning-Based Semantic Segmentation of Remote Sensing Images: A Survey

Huang,

Jiang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation of remote sensing images (SSRSI), which aims to assign a category to each pixel in remote sensing images, plays a vital role in a broad range of applications, such as environmental monitoring, urban planning, and land resource utilization. Recently, with the successful application of deep learning in remote sensing, a substantial amount of work has been aimed at developing SSRSI methods using deep learning models. In this survey, we provide a comprehensive review of SSRSI. Firstly, we review the current mainstream semantic segmentation models based on deep learning. Next, we analyze the main challenges faced by SSRSI and comprehensively summarize the current research status of deep learning-based SSRSI, especially some new directions in SSRSI are outlined, including semi-supervised and weakly-supervised SSRSI, unsupervised domain adaption (UDA) in SSRSI, multi-modal data fusion-based SSRSI, and pretrained models for SSRSI. Then, we examine the most widely used datasets and metrics and review the quantitative results and experimental performance of some representative methods of SSRSI. At last, we discuss promising future research directions in this area.

show abstract

Section: ) What To Fusementioning

confidence: 99%

Section: Fusion Of Multispectral Image and Lidar Datamentioning

confidence: 99%

Deep-Learning-Based Semantic Segmentation of Remote Sensing Images: A Survey

Huang,

Jiang,

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Supervised learning methods can obtain highly accurate segmentation results using a large amount of labeled data, especially if the training data are sufficient and wellrepresented. In recent years, unsupervised semantic segmentation methods [13,14] for RSIs can classify features without pre-labeled training data. These methods are very effective in dealing with large-scale remote sensing data because the methods do not require an expensive and time-consuming manual labeling process.…”

Section: Introductionmentioning

confidence: 99%

EAD-Net: Efficiently Asymmetric Network for Semantic Labeling of High-Resolution Remote Sensing Images with Dynamic Routing Mechanism

Hu,

Wang,

2024

Remote Sensing

View full text Add to dashboard Cite

Semantic labeling of high-resolution remote sensing images (HRRSIs) holds a significant position in the remote sensing domain. Although numerous deep-learning-based segmentation models have enhanced segmentation precision, their complexity leads to a significant increase in parameters and computational requirements. While ensuring segmentation accuracy, it is also crucial to improve segmentation speed. To address this issue, we propose an efficient asymmetric deep learning network for HRRSIs, referred to as EAD-Net. First, EAD-Net employs ResNet50 as the backbone without pooling, instead of the RepVGG block, to extract rich semantic features while reducing model complexity. Second, a dynamic routing module is proposed in EAD-Net to adjust routing based on the pixel occupancy of small-scale objects. Concurrently, a channel attention mechanism is used to preserve their features even with minimal occupancy. Third, a novel asymmetric decoder is introduced, which uses convolutional operations while discarding skip connections. This not only effectively reduces redundant features but also allows using low-level image features to enhance EAD-Net’s performance. Extensive experimental results on the ISPRS 2D semantic labeling challenge benchmark demonstrate that EAD-Net achieves state-of-the-art (SOTA) accuracy performance while reducing model complexity and inference time, while the mean Intersection over Union (mIoU) score reaching 87.38% and 93.10% in the Vaihingen and Potsdam datasets, respectively.

show abstract