An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery

Yang, Xuan; Li, Shanshan; Chen, Zhengchao; Chanussot, Jocelyn; Jia, Xiuping; Zhang, Bing; Li, Baipeng; Chen, Pan

doi:10.1016/j.isprsjprs.2021.05.004

Cited by 113 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning the Potsdam dataset, the overall results (shown in Table II) of U-Net by itself are more precise than those obtained on the Vaihingen dataset (comparable with the results recently shown in [53], [54]). However, as the GTs become scarcer, the proposed architecture progressively obtains higher recalls for the smallest classes (e.g., "trees" and "cars").…”

Section: Resultssupporting

confidence: 84%

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Pastorino

Moser

Zerubia

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep learning is currently the dominant approach to image classification and segmentation, but the performances of deep learning methods are remarkably influenced by the quantity and quality of the ground truth (GT) used for training. In this paper, a deep learning method is presented to deal with the semantic segmentation of very high resolution (VHR) remote sensing data in the case of scarce GT. The main idea is to combine a specific type of deep convolutional neural networks (CNNs), namely, fully convolutional networks (FCNs), with probabilistic graphical models (PGMs). Our method takes advantage of the intrinsic multiscale behavior of FCNs to deal with multiscale data representations and to connect them to a hierarchical Markov model (e.g., making use of a quadtree). As a consequence, the spatial information present in the data is better exploited, allowing a reduced sensitivity to GT incompleteness to be obtained. The marginal posterior mode criterion is used for inference in the proposed framework. To assess the capabilities of the proposed method, the experimental validation is conducted with the ISPRS 2D Semantic Labeling Challenge datasets on the cities of Vaihingen and Potsdam, with some modifications to simulate the spatially sparse GTs that are common in real remote sensing applications. The results are quite significant, as the proposed approach exhibits a higher producer accuracy than the standard FCNs considered and especially mitigates the impact of scarce GTs on minority classes and small spatial details.

show abstract

Section: Resultssupporting

confidence: 84%

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Pastorino

Moser

Zerubia

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Many related works have progressed in two ways: the designed architecture and the modified mechanism in semantic segmentation. For the sake of algorithm efficiency, they explored fine-grained segmentation with a designed architecture, such as enlarging receptive fields [19] or constructing explicit spatial relations [20][21][22]. In addition, some works altered the framework of semantic segmentation and successfully applied them in aerial image analysis [23][24][25].…”

Section: Semantic Segmentation In Aerial Image Analysismentioning

confidence: 99%

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

Sun¹,

Xia

Dai³

2022

Remote Sensing

View full text Add to dashboard Cite

High-resolution remote sensing images have been put into the application in remote sensing parsing. General remote sensing parsing methods based on semantic segmentation still have limitations, which include frequent neglect of tiny objects, high complexity in image understanding and sample imbalance. Therefore, a controllable fusion module (CFM) is proposed to alleviate the problem of implicit understanding of complicated categories. Moreover, an adaptive edge loss function (AEL) was proposed to alleviate the problem of the recognition of tiny objects and sample imbalance. Our proposed method combining CFM and AEL optimizes edge features and body features in a coupled mode. The verification on Potsdam and Vaihingen datasets shows that our method can significantly improve the parsing effect of satellite images in terms of mIoU and MPA.

show abstract

“…Feature extraction based on deep learning can effectively overcome the limitations of traditional RS image processing methods [31] and provide a feasible way to carry out subject-sensitive hashing. In the related methods of deep learning, the attention mechanism enables the network to dynamically select a subset of input attributes in a given inputoutput pair setting to improve the accuracy of decision making [32].…”

Section: Ph(i) = Ph Imentioning

confidence: 99%

AAU-Net: Attention-Based Asymmetric U-Net for Subject-Sensitive Hashing of Remote Sensing Images

Ding

Chen

Wang³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The prerequisite for the use of remote sensing images is that their security must be guaranteed. As a special subset of perceptual hashing, subject-sensitive hashing overcomes the shortcomings of the existing perceptual hashing that cannot distinguish between “subject-related tampering” and “subject-unrelated tampering” of remote sensing images. However, the existing subject-sensitive hashing still has a large deficiency in robustness. In this paper, we propose a novel attention-based asymmetric U-Net (AAU-Net) for the subject-sensitive hashing of remote sensing (RS) images. Our AAU-Net demonstrates obvious asymmetric structure characteristics, which is important to improve the robustness of features by combining the attention mechanism and the characteristics of subject-sensitive hashing. On the basis of AAU-Net, a subject-sensitive hashing algorithm is developed to integrate the features of various bands of RS images. Our experimental results show that our AAU-Net-based subject-sensitive hashing algorithm is more robust than the existing deep learning models such as Attention U-Net and MUM-Net, and its tampering sensitivity remains at the same level as that of Attention U-Net and MUM-Net.

show abstract

An attention-fused network for semantic segmentation of very-high-resolution remote sensing imagery

Cited by 113 publications

References 27 publications

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Controllable Fused Semantic Segmentation with Adaptive Edge Loss for Remote Sensing Parsing

AAU-Net: Attention-Based Asymmetric U-Net for Subject-Sensitive Hashing of Remote Sensing Images

Contact Info

Product

Resources

About