Multi-scale Contextual Information Research Articles

SC-EADNet: A Self-Supervised Contrastive Efficient Asymmetric Dilated Network for Hyperspectral Image Classification

Unsupervised and semisupervised feature learning has recently emerged as an effective way to reduce the reliance on expensive data collection and annotation for hyperspectral image (HSI) analysis. Existing unsupervised and semisupervised convolutional neural network (CNN)-based HSI classification works still face two challenges: underutilization of pixel-wise multiscale contextual information for feature learning and expensive computational cost, for example, large floating-point operations per seconds (FLOPs), due to the lack of lightweight design. To utilize the unlabeled pixels in the HSIs more efficiently, we propose a self-supervised contrastive efficient asymmetric dilated network (SC-EADNet) for HSI classification. There are two novelties in the SC-EADNet. First, a self-supervised multiscale pixel-wise contextual feature learning model is proposed, which generates multiple patches around each hyperspectral pixel and develops a contrastive learning framework to learn from these patches for HSI classification. Second, a lightweight feature extraction network EADNet, composed of multiple plug-and-play efficient asymmetric dilated convolution (EADC) blocks, is designed and inserted into the contrastive learning framework. The EADC block adopts different dilation rates to capture the spatial information of objects with varying shapes and sizes. Compared with other unsupervised, semisupervised, and supervised learning methods, our SC-EADNet provides competitive classification performance on four hyperspectral datasets, including Indian Pines, Pavia University, Salinas, and Houston 2013, but few FLOPs and fast computational speed.

SCA-Net: A Multiscale Building Segmentation Network Incorporating a Dual-Attention Mechanism

The traditional deep learning networks in remote sensing image building segmentation have problems such as incomplete internal extraction, low accuracy of edge segmentation, and difficult prediction of irregular targets. Based on this, this paper proposes the network SCA-Net, which fuses the dense connection feature pyramid (DCFP) module and the spatial and channel attention mechanisms (SCA) module, for high precision automatic extraction of building contours. First, the DCFP module is used to obtain a large range of multi-scale contextual information without sacrificing the spatial resolution of features, thus improving the recognition rate of small-sized buildings. Second, SCA module is used to enhance feature learning ability of building pixels and suppress irrelevant feature information input. Finally, a fully convolutional asymmetric encoder-decoder structure is designed to obtain the final building segmentation results by gradually fusing the features and decoding them. The results on the WHU dataset as well as the CHN dataset show that the extraction of buildings using this method has good extraction results and high accuracy performance, outperforming several comparable advanced networks.

A Robust One-Stage Detector for Multiscale Ship Detection With Complex Background in Massive SAR Images

With the development of synthetic aperture radar (SAR) imaging and deep learning, SAR ship detection based on convolutional neural networks (CNNs) has been extensively applied in the last few years. Nevertheless, there are two main obstacles in SAR ship detection: 1) the SAR images have too much noise, such as the interference from land area, making it difficult to distinguish ship objects from the surrounding background, and 2) due to the multiscale characteristics of ship objects, there are numerous false negatives in the detection results, especially for small objects. To alleviate the above problems, we propose a one-stage ship detector with strong robustness against scale changes and various interferences. First, to mitigate the disturbance from complex background, a coordinate attention module (CoAM) is introduced for obtaining more representative semantic features to accurately locate and distinguish ship objects. Second, a receptive field increased module (RFIM) is devised to capture multiscale contextual information to improve the detection performance for ships with diverse scales. Finally, we verify the robustness of our method on several public SAR datasets, i.e., SAR-Ship-Dataset, high-resolution SAR images dataset (HRSID), and SAR ship detection dataset (SSDD). The experimental results demonstrate that the proposed method has a competitive performance, exceeding other state-of-the-art methods by at least 2.6% AP <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">50</sub> on HRSID.

A Cross-Level Spectral–Spatial Joint Encode Learning Framework for Imbalanced Hyperspectral Image Classification

Convolutional neural networks (CNNs) have dominated the research of hyperspectral image (HSI) classification, attributing to the superior feature representation capacity. Patch-free global learning (FPGA) as a fast learning framework for HSI classification has received wide interest. Despite their promising results from the perspective of fast inference, recent works have difficulty modeling spectral-spatial relationships with imbalanced samples. In this paper, we revisit the encoder–decoder-based fully convolutional network (FCN) and propose a cross-level spectral-spatial joint encoding framework (CLSJE) for Imbalanced HSI classification. First, a multi-scale input encoder and multiple-to-one multi-scale features connection are introduced to obtain abundant features and facilitate multi-scale contextual information flow between encoder and decoder. Second, in the encoder layer, we propose the spectral-spatial joint attention (SSJA) mechanism consisting of the high-frequency spatial attention (HFSA) and spectral-transform channel attention (STCA). HFSA and STCA encode spectral-spatial features jointly to improve the learning of the discriminative spectral-spatial features. Powered by these two components, CLSJE enjoys a high capability to capture both spatial and spectral dependencies for HSI classification. Besides, a class-proportion sampling strategy is developed to increase the attention to insufficiency samples. Extensive experiments demonstrate the superiority of our proposed CLSJE both at classification accuracy and inference speed, and show the state-of-the-art results on four benchmark datasets. Code can be obtained at: https://github.com/yudadabing/CLSJE.

LWCDnet: A Lightweight Network for Efficient Cloud Detection in Remote Sensing Images

Cloud detection is the task of detecting cloud areas in remote sensing images, and it has attracted extensive research interest. Recently, deep learning-based methods have been proposed and achieved great performance for cloud detection. However, due to the satellite’s limitation in storage and memory, existing deep learning approaches, which suffer from extensive computation and large model size, are almost impossible to be deployed on satellites. To fill this gap, we target at studying effective and efficient cloud detection solutions that are suitable for satellites. In this paper, we develop a lightweight autoencoder-based cloud detection method, namely LWCDnet. In the encoder part, the designed novel lightweight dual-branch block (LWDBB) in the backbone extracts spatial and contextual information concurrently. Moreover, a lightweight feature pyramid module (LWFPM) is proposed to capture high-level multi-scale contextual information. In the decoder part, the lightweight feature fusion module (LWFFM) compensates for the missing spatial and detail information from the encoder to the high-level feature maps. We evaluate the proposed method on two public datasets: LandSat8 and MODIS. Extensive experiments demonstrate that the proposed LWCDnet achieves comparable accuracy as the-state-of-art cloud detection methods and lightweight semantic segmentation algorithms. Meantime LWCDnet has much less computation burden with smaller model size.

Geospatial Transformer Is What You Need for Aircraft Detection in SAR Imagery

Although deep learning techniques have achieved noticeable success in aircraft detection, the scale heterogeneity, position difference, complex background interference, and speckle noise keep aircraft detection in large-scale synthetic aperture radar (SAR) images challenging. To solve these problems, we propose the geospatial transformer framework and implement it as a three-step target detection neural network, namely, the image decomposition, the multiscale geospatial contextual attention network (MGCAN), and result recomposition. First, the given large-scale SAR image is decomposed into slices via sliding windows according to the image characteristics of the aircraft. Second, slices are input into the MGCAN network for feature extraction, and the cluster distance nonmaximum suppression (CD-NMS) is utilized to determine the bounding boxes of aircraft. Finally, the detection results are produced via recomposition. Two innovative geospatial attention modules are proposed within MGCAN, namely, the efficient pyramid convolution attention fusion (EPCAF) module and the parallel residual spatial attention (PRSA) module, to extract multiscale features of the aircraft and suppress background noise. In the experiment, four large-scale SAR images with 1-m resolution from the Gaofen-3 system are tested, which are not included in the dataset. The results indicate that the detection performance of our geospatial transformer is better than Faster R-CNN, SSD, Efficientdet-D0, and YOLOV5s. The geospatial transformer integrates deep learning with SAR target characteristics to fully capture the multiscale contextual information and geospatial information of aircraft, effectively reduces complex background interference, and tackles the position difference of targets. It greatly improves the detection performance of aircraft and offers an effective approach to merge SAR domain knowledge with deep learning techniques.

A Deformable Attention Network for High-Resolution Remote Sensing Images Semantic Segmentation

Deformable convolutional networks (DCNs) can mitigate the inherent limited geometric transformation. We reformulate the spatialwise attention mechanism using DCNs in this article for semantic segmentation of high-resolution remote sensing (HRRS) images. It combines the sparse spatial sampling strategy and the long-range relationship modeling capability, namely, deformable attention module (DAM). Such locality awareness, more adaptable to HRRS image structures, can capture each pixel’s neighboring structural information. A reasonable multiscale deformable attention net (MDANet) is designed for the HRRS image semantic segmentation with a slightly increased computational cost based on the proposed DAM. Specifically, standard convolutional layers in the raw ResNet50 are equipped with a DAM to control sampling over a broader range of feature levels and aggregate multiscale context information. The experimental results evaluated on Vaihingen and DeepGlobe Land Cover Classification datasets show that the performance accuracy of MDANet is improved by 7.77% and 8.45% compared with the backbone network (ResNet50) in terms of Miou evaluation, respectively. Furthermore, a DAM can perform better than a global spatial attention mechanism with less computation on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3 \times 64 \times 64$ </tex-math></inline-formula> feature map. In addition, the added ablation studies demonstrate the effectiveness and efficiency of the DAM and multiscale strategy, respectively. Moreover, the sensitivity of critical hyperparameters is analyzed.

Real-time pixel-wise grasp affordance prediction based on multi-scale context information fusion

PurposeThis paper aims to use fully convolutional network (FCN) to predict pixel-wise antipodal grasp affordances for unknown objects and improve the grasp detection performance through multi-scale feature fusion.Design/methodology/approachA modified FCN network is used as the backbone to extract pixel-wise features from the input image, which are further fused with multi-scale context information gathered by a three-level pyramid pooling module to make more robust predictions. Based on the proposed unify feature embedding framework, two head networks are designed to implement different grasp rotation prediction strategies (regression and classification), and their performances are evaluated and compared with a defined point metric. The regression network is further extended to predict the grasp rectangles for comparisons with previous methods and real-world robotic grasping of unknown objects.FindingsThe ablation study of the pyramid pooling module shows that the multi-scale information fusion significantly improves the model performance. The regression approach outperforms the classification approach based on same feature embedding framework on two data sets. The regression network achieves a state-of-the-art accuracy (up to 98.9%) and speed (4 ms per image) and high success rate (97% for household objects, 94.4% for adversarial objects and 95.3% for objects in clutter) in the unknown object grasping experiment.Originality/valueA novel pixel-wise grasp affordance prediction network based on multi-scale feature fusion is proposed to improve the grasp detection performance. Two prediction approaches are formulated and compared based on the proposed framework. The proposed method achieves excellent performances on three benchmark data sets and real-world robotic grasping experiment.

Semantic Segmentation of High-Resolution Airborne Images with Dual-Stream DeepLabV3+

In geospatial applications such as urban planning and land use management, automatic detection and classification of earth objects are essential and primary subjects. When the significant semantic segmentation algorithms are considered, DeepLabV3+ stands out as a state-of-the-art CNN. Although the DeepLabV3+ model is capable of extracting multi-scale contextual information, there is still a need for multi-stream architectural approaches and different training approaches of the model that can leverage multi-modal geographic datasets. In this study, a new end-to-end dual-stream architecture that considers geospatial imagery was developed based on the DeepLabV3+ architecture. As a result, the spectral datasets other than RGB provided increments in semantic segmentation accuracies when they were used as additional channels to height information. Furthermore, both the given data augmentation and Tversky loss function which is sensitive to imbalanced data accomplished better overall accuracies. Also, it has been shown that the new dual-stream architecture using Potsdam and Vaihingen datasets produced 88.87% and 87.39% overall semantic segmentation accuracies, respectively. Eventually, it was seen that enhancement of the traditional significant semantic segmentation networks has a great potential to provide higher model performances, whereas the contribution of geospatial data as the second stream to RGB to segmentation was explicitly shown.

MIFNet: A lightweight multiscale information fusion network

Semantic segmentation technique plays a crucial role in Internet of Things applications, such as industrial robotics and self-driving. Recently deep learning approaches have boosted semantic segmentation accuracy greatly. However, their comprehensive performance in terms of accuracy and efficiency is still far from satisfactory. We observe that (1) accuracy-oriented methods rely on numerous convolution layers and sophisticated architectures, which result in heavy computational complexity and usually take a long time for inference; (2) efficiency-oriented methods fail to capture the multiscale context information for discriminative representations during the feature fusion process, thus leading to suboptimal performance. Previous semantic segmentation approaches fail to address these two challenges simultaneously. To tackle the dilemma of precise segmentation and efficient inference, we propose a novel lightweight Multiscale Information Fusion Network (MIFNet). Specifically, the proposed MIFNet mainly consists of two core components, that is, Pyramid Refinement Connection Module (PRCM) and Lightweight Information Fusion Module (LIFM). The PRCM exploits skip learning to establish dependency between different stages. Meanwhile, the pyramid attention mechanism (PAM) in PRCM, which adjusts the weight of hybrid pyramid attention vector to refine spatial features of low-level, is developed to alleviate the semantic gap. Moreover, the LIFM is designed to detect objects at multiple scales from the global-local perspective. In LIFM, the proposed multiscale dense concatenation (MDC) adopts various dilated convolution to extract multiscale local context information. Extensive experimental results on benchmarks data sets demonstrate the significantly better performance of the proposed MIFNet compared with most existing state-of-the-art methods.

MFAUNet: Multiscale feature attentive U‐Net for cardiac MRI structural segmentation

The accurate and robust automatic segmentation of cardiac structures in magnetic resonance imaging (MRI) is significant in calculating cardiac clinical functional indices, and diagnosing heart diseases. Most U-Net based methods use pooling, transposed convolution, and skip connection operations to integrate the multiscale features for improved segmentation in cardiac MRI. However, this architecture lacks adequate semantic connection between the channel and spatial information, and robustness in segmenting objects with significant shape variations. In this paper, a new multiscale feature attentive U-Net for cardiac MRI structural segmentation method is proposed. An attention mechanism is adopted after concatenating the multi-level features to aggregate different scale features and determine on which features to focus. Cascade and parallel dilated convolution is also employed in the decoder blocks and skip connection is employed to enhance the ability of sensing receptive fields for multiscale context information. Furthermore, deep supervision approach with a loss function that combines the dice and cross-entropy losses to reduce overfitting and ensure better prediction is introduced. The proposed method was evaluated on three public cardiac datasets. The experimental results indicate that the method achieved competitive segmentation performance with the three datasets, which verifies the robustness and generalisability of the proposed network. In comparison with conventional U-Net methods, the model leverages attention mechanism and dilated convolution block, which increases the semantic connection between the channel and the spatial information, and improves the robustness of the right ventricle segmentation performance. From the view of the Dice scores and segmentation results, the multiscale feature attentive U-Net method is one of effective methods in segmenting cardiac MRI structures.

Contextual Information Aided Generative Adversarial Network for Low-Light Image Enhancement

Low-light image enhancement has been gradually becoming a hot research topic in recent years due to its wide usage as an important pre-processing step in computer vision tasks. Although numerous methods have achieved promising results, some of them still generate results with detail loss and local distortion. In this paper, we propose an improved generative adversarial network based on contextual information. Specifically, residual dense blocks are adopted in the generator to promote hierarchical feature interaction across multiple layers and enhance features at multiple depths in the network. Then, an attention module integrating multi-scale contextual information is introduced to refine and highlight discriminative features. A hybrid loss function containing perceptual and color component is utilized in the training phase to ensure the overall visual quality. Qualitative and quantitative experimental results on several benchmark datasets demonstrate that our model achieves relatively good results and has good generalization capacity compared to other state-of-the-art low-light enhancement algorithms.

Learning interlaced sparse Sinkhorn matching network for video super-resolution

How to effectively fuse inter- and intra-frame spatio-temporal information plays a key role in video super-resolution (VSR). Most existing works rely heavily on the accuracy of motion estimation and compensation for spatio-temporal feature alignment. However, they cannot perform well when suffering from large-scale and complex motions. To this end, this paper introduces an efficient and effective Interlaced Sparse Sinkhorn Matching (ISSM) network for VSR, which aligns supporting frames with the reference one in the feature space by learning optimal matching between image regions across frames. Specifically, the ISSM divides the input dense affinity matrix into two sparse block matrixes: one can match long-distance regions while the other can match short-distance regions, and then we leverage an efficient Sinkhorn method on each block to learn optimal matching. Moreover, we insert a residual atrous spatial pyramid pooling module before the ISSM, which can flexibly generate multi-scale features frame by frame to capture the multi-scale context information in images. The aligned features of each adjacent frame are then fed to a bidirectional temporal fusion module to capture the rich temporal information. Finally, the fused features are sent into a frame-wise dynamic reconstruction network to produce an HR frame. Extensive evaluations on three benchmark datasets demonstrate the superiority of our method over the state-of-the-art methods in terms of PSNR and SSIM.

Airport small object detection based on feature enhancement

Video object detection is essential for airport surface surveillance, but the objects on the scene are mostly small objects with low resolution, they have no obvious feature information. Due to the scale differences of the objects and the fixed receptive field on the feature maps, detectors cannot model multi-scale context information and cover all objects. In addition, although the video detection algorithm can be used as a method to solve the problem of small object detection, the temporal feature fusion method of current video detection is very dependent on the quality of a single feature map. Therefore, this paper aims to enhance the features of small objects of a single image. First, an attentional multi-scale feature fusion enhancement (A-MSFFE) network is built on the memory-enhanced global-local aggregation (MEGA) to supplement semantic and spatial information of small objects. Then, a context feature enhancement (CFE) module is designed for obtaining different receptive fields through different dilated convolutions. Meanwhile, a video detection dataset about the airport is established. Finally, the experimental results show that the proposed method can improve the detection accuracies of small objects and outperform other state-of-the-art video object detection algorithms in self-built airport dataset.

Parallel multiscale context-based edge-preserving optical flow estimation with occlusion detection

Although convolutional neural network (CNN)-based optical flow approaches have exhibited good performance in terms of computational accuracy and efficiency in recent years, the issue of edge-blurring caused by motion occlusions remains. In this paper, we propose a parallel multiscale context-based edge-preserving optical flow estimation method with occlusion detection, named PMC-PWC. First, we exploit a parallel multiscale context (PMC) network for occlusion detection, in which the proposed PMC model is able to aggregate the multiscale context information to develop the performance of occlusion detection near motion boundaries. Second, we combine the PMC model with a context network to plan an occlusion estimation module and incorporate it into a pyramid, warping, and cost volume model to construct an edge-preserving optical flow computation network. Third, we design a novel loss function including an endpoint error (EPE)-based loss, a binary cross-entropy loss and an edge loss to supervise the proposed PMC-PWC network to produce optical flow and occlusion simultaneously. Finally, we run the proposed PMC-PWC method on the MPI-Sintel and KITTI datasets to conduct a comprehensive comparison with several state-of-the-art approaches. The experimental results indicate that the proposed PMC-PWC method performed well in terms of both accuracy and robustness, especially due to the significant benefits of edge preservation and occlusion handling.

EMS-Net: Enhanced Multi-Scale Network for Polyp Segmentation.

In recent years, polyp segmentation plays an important role in the diagnosis and treatment of colorectal cancer. Accurate segmentation of polyps is very challenging due to different sizes, shapes, and unclear boundaries. Making full use of multi-scale contextual information to segment polyps may bring better results. In this paper, we propose an enhanced multi-scale network for accurate polyp segmentation. It is composed of a multi-scale connected baseline (U-Net+++), a multi-scale backbone (Res2Net), three Receptive Field Block (RFB) modules, and four Local Context Attention (LCA) modules. Specifically, the baseline's multi-scale skip connections can aggregate features in both low-level and high-level layers. We have evaluated our model on three publicly available and challenging datasets (EndoScene, CVC-ClinicDB, Kvasir-SEG). Compared with other methods, our model achieves SOTA performance. It is noteworthy that our model is the only network that has achieved over 0.900 mean Dice on EndoScene and CVC-ClinicDB.

Liver tumor segmentation using a new asymmetrical dilated convolutional semantic segmentation network in CT images

AbstractLiver cancer has become one of the commonly occurring cancers in men and women. The segmented computed tomography (CT) image of the tumor is the major source for a doctor to diagnose liver diseases. This article proposes a fully automatic system based on an asymmetric dilated convolutional encoder–decoder neural (ADCEDN) network for the problem of accurately extracting the liver and tumor from abdominal CT slices. Specifically, two ADCEDN networks are used in a cascaded form to perform both liver and liver abnormality segmentation. We enrich the encoder module by incorporating the multiscale contextual information through dilated convolutions that enhance the capacity and efficiency of the network. Hybrid dilated convolution across depths perform depth‐wise separable convolution by providing a less steep increase in dilation rate and thus denser sampling that can reduce the computation cost and several metrics while maintaining better performance. Also, the encoder–decoder network is made asymmetric, thereby making the network less complex and more generalizable. The suggested method produced an average dice similarity coefficient score of 96.54% and 76.16% for liver segmentation and liver abnormality segmentation on the 3D Image Reconstruction for Comparison of Algorithm Database data set and 96.42% and 75.7% on the Liver Tumor Segmentation data set. The test outcomes show that the proposed ADCEDN attains state‐of‐the‐art performance in both segmentation of liver and tumors.

Multi-Supervised Encoder-Decoder for Image Forgery Localization

Image manipulation localization is one of the most challenging tasks because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. Unlike many existing solutions, we employ a semantic segmentation network, named Multi-Supervised Encoder–Decoder (MSED), for the detection and localization of forgery images with arbitrary sizes and multiple types of manipulations without extra pre-training. In the basic encoder–decoder framework, the former encodes multi-scale contextual information by atrous convolution at multiple rates, while the latter captures sharper object boundaries by applying upsampling to gradually recover the spatial information. The additional multi-supervised module is designed to guide the training process by multiply adopting pixel-wise Binary Cross-Entropy (BCE) loss after the encoder and each upsampling. Experiments on four standard image manipulation datasets demonstrate that our MSED network achieves state-of-the-art performance compared to alternative baselines.

Evaluation of Deep Learning Segmentation Models for Detection of Pine Wilt Disease in Unmanned Aerial Vehicle Images

Pine wilt disease (PWD) is a serious threat to pine forests. Combining unmanned aerial vehicle (UAV) images and deep learning (DL) techniques to identify infected pines is the most efficient method to determine the potential spread of PWD over a large area. In particular, image segmentation using DL obtains the detailed shape and size of infected pines to assess the disease’s degree of damage. However, the performance of such segmentation models has not been thoroughly studied. We used a fixed-wing UAV to collect images from a pine forest in Laoshan, Qingdao, China, and conducted a ground survey to collect samples of infected pines and construct prior knowledge to interpret the images. Then, training and test sets were annotated on selected images, and we obtained 2352 samples of infected pines annotated over different backgrounds. Finally, high-performance DL models (e.g., fully convolutional networks for semantic segmentation, DeepLabv3+, and PSPNet) were trained and evaluated. The results demonstrated that focal loss provided a higher accuracy and a finer boundary than Dice loss, with the average intersection over union (IoU) for all models increasing from 0.656 to 0.701. From the evaluated models, DeepLLabv3+ achieved the highest IoU and an F1 score of 0.720 and 0.832, respectively. Also, an atrous spatial pyramid pooling module encoded multiscale context information, and the encoder–decoder architecture recovered location/spatial information, being the best architecture for segmenting trees infected by the PWD. Furthermore, segmentation accuracy did not improve as the depth of the backbone network increased, and neither ResNet34 nor ResNet50 was the appropriate backbone for most segmentation models.

Multi-scale context extractor network for water-body extraction from high-resolution optical remotely sensed images

Water-body surveying and mapping is of great significance for water resources utilization, flood monitoring, and environmental protection. However, due to distribution diversities, shape and size variations, and complex scenarios of water-bodies, it is still challengeable to accurately and efficiently extract water-bodies from high-resolution remotely sensed images. In this paper, we propose a multi-scale context extractor network, termed as MSCENet, for delineating water-bodies from high-resolution optical remotely sensed images. The MSCENet mainly contains three key parts: a multi-scale feature encoder, a feature decoder, and a context feature extractor module. To address shape and size variations of water-bodies, the Res2Net is used in the feature encoder to extract rich multi-scale information of water-bodies. The context extractor module is composed of an assorted dilated convolution unit and a complex multi-kernel pooling unit, which further extracts multi-scale contextual information to generate high-level feature maps. The robustness and effectiveness of our MSCENet have been evaluated on two public datasets: LandCover.ai Data Set and DeepGlobe Data Set. Comparative experiments indicate the superiority and applicability of the MSCENet in water-body extraction.