DSPCANet: Dual-Channel Scale-Aware Segmentation Network With Position and Channel Attentions for High-Resolution Aerial Images

Li, Yuncheng; Li, Heng-Chao; Hu, Wen-Shuai; Yu, Hongxian

doi:10.1109/jstars.2021.3102137

Cited by 14 publications

(10 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen from Table 9, the results of our proposed model MQANet show better results on both datasets. On the Vaihingen dataset, our MQANet network has higher Mean F1 and OA than other networks, and on the Potsdam dataset, our MQANet network has higher Mean F1 than other networks, and only OA is 0.08% lower than DSPCANet [15]. Mean F1 score for classification is calculated as the harmonic mean of precision and recall [22], and OA is the ratio of the number of correct pixels to the total number of pixels.…”

Section: Discussion Of Overall Experimental Resultsmentioning

confidence: 99%

“…OA = TP + TN TP + TN + FP + FN (15) with the following terms: True Positive example (TP), False Positive Example (FP), True Negative example (TN), False Negative example (FN).…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…EFCNet [14] introduces the separable convolutional module (SCM) to alleviate the problem of numerous parameters for the semantic segmentation of high-resolution remote sensing images. DSPCANet [15] introduces the internal residual block (R2_Block) to enhance the receptive field of the network and learn the ground feature representation from additional DSM images. Sharifi et al [16] proposed the ResUNet-a model with post-processing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MQANet: Multi-Task Quadruple Attention Network of Multi-Object Semantic Segmentation from Remote Sensing Images

Sui

Tong

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Multi-object semantic segmentation from remote sensing images has gained significant attention in land resource surveying, global change monitoring, and disaster detection. Compared to other application scenarios, the objects in the remote sensing field are larger and have a wider range of distribution. In addition, some similar targets, such as roads and concrete-roofed buildings, are easily misjudged. However, existing convolutional neural networks operate only in the local receptive field, and this limits their capacity to represent the potential association between different objects and surrounding features. This paper develops a Multi-task Quadruple Attention Network (MQANet) to address the above-mentioned issues and increase segmentation accuracy. The MQANet contains four attention modules: position attention module (PAM), channel attention module (CAM), label attention module (LAM), and edge attention module (EAM). The quadruple attention modules obtain global features by expanding the receptive fields of the network and introducing spatial context information in the label. Then, a multi-tasking mechanism which splits a multi-category segmentation task into several binary-classification segmentation tasks is introduced to improve the ability to identify similar objects. The proposed MQANet network was applied to the Potsdam dataset, the Vaihingen dataset and self-annotated images from Chongzhou and Wuzhen (CZ-WZ), representative cities in China. Our MQANet performs better over the baseline net by a large margin of +6.33 OA and +7.05 Mean F1-score on the Vaihingen dataset, +3.57 OA and +2.83 Mean F1-score on the Potsdam dataset, and +3.88 OA and +8.65 Mean F1-score on the self-annotated dataset (CZ-WZ dataset). In addition, each image execution time of the MQANet model is reduced 66.6 ms compared to UNet. Moreover, the effectiveness of MQANet was also proven by comparative experiments with other studies.

show abstract

Section: Discussion Of Overall Experimental Resultsmentioning

confidence: 99%

“…OA = TP + TN TP + TN + FP + FN (15) with the following terms: True Positive example (TP), False Positive Example (FP), True Negative example (TN), False Negative example (FN).…”

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MQANet: Multi-Task Quadruple Attention Network of Multi-Object Semantic Segmentation from Remote Sensing Images

Sui

Tong

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Many parallel atrous convolutions layers with different rates are fused to take the contextual information at various scales. Atrous convolution expands the field of view to capture multi-scale features and also generates more parameters (Li et al, 2021). In the proposed algorithm, ASPP operates as a bridge between encoder and decoder in the both side of networks, as shown in Figure 1.…”

Section: Atrous Spatial Pyramidal Poolingmentioning

confidence: 99%

Building Change Detection by W-Shape Resunet++ Network With Triple Attention Mechanism

Eftekhari

Samadzadegan²,

Javan³

2023

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Building change detection in high resolution remote sensing images is one of the most important and applied topics in urban management and urban planning. Different environmental illumination conditions and registration problem are the most error resource in the bitemporal images that will cause pseudochanges in results. On the other hand, the use of deep learning technologies especially convolutional neural networks (CNNs) has been successful and considered, but usually causes the loss of shape and detail at the edges. Accordingly, we propose a W-shape ResUnet++ network in which images with different environmental conditions enter the network independently. ResUnet++ is a network with residual blocks, triple attention blocks and Atrous Spatial Pyramidal Pooling. ResUnet++ is used on both sides of the network to extract deeper and discriminator features. This improves the channel and spatial inter-dependencies, while at the same time reducing the computational cost. After that, the Euclidean distance between the features is computed and the deconvolution is done. Also, a dual loss function is designed that used the weighted binary cross entropy to solve the unbalance between the changed and unchanged data in change detection training data and in the second part, we used the mask–boundary consistency constraints that the condition of converging the edges of the training data and the predicted edge in the loss function has been added. We implemented the proposed method on two remote sensing datasets and then compared the results with state-of-the-art methods. The F1 score improved 1.52 % and 4.22 % by using the proposed model in the first and second dataset, respectively.

show abstract

“…Then, the FPN is reconstructed in a bottom-top format to reduce the span between high-level feature maps and low-level ones, which can enrich detail information of high-level feature maps and avoid loss of semantic information from channel reduction. In addition, a channel attention module (CAM) [37] is introduced to reconstruct the FPN to connect adjacent feature layers while generating salient features. The CAM uses pooling operations (Max-Pool and AvgPool) to generate channel context descriptors and then outputs channel attention feature maps through a shared network, which consists of a multilayer perceptron (MLP).…”

Section: Ship Detectormentioning

confidence: 99%

DD-Net: A Dual Detector Network for Multilevel Object Detection in Remote-Sensing Images

Zhang

Wang

2022

Journal of Sensors

View full text Add to dashboard Cite

With the recent development of deep convolutional neural network (CNN), remote sensing for ship detection methods has achieved enormous progress. However, current methods focus on the whole ships and fail on the component’s detection of a ship. To detect ships from remote-sensing images in a more refined way, we employ the inherent relationship between ships and their critical parts to establish a multilevel structure and propose a novel framework to improve the performance in identifying the multilevel objects. Our framework, named the dual detector network (DD-Net), consists of two carefully designed detectors, one for ships (the ship detector) and the other for their critical parts (the critical part detector), for detecting the critical parts in a coarse-to-fine manner. The ship detector offers detection results of the ship, based on which the critical part detector detects small critical parts inside each ship region. The framework is trained in an end-to-end way by optimizing the multitask loss. Due to the lack of publicly available datasets for critical part detection, we build a new dataset named RS-Ship with 1015 remote-sensing images and 2856 annotations. Experiments on the HRSC2016 dataset and the RS-Ship dataset show that our method performs well in the detection of ships and critical parts.

show abstract

DSPCANet: Dual-Channel Scale-Aware Segmentation Network With Position and Channel Attentions for High-Resolution Aerial Images

Cited by 14 publications

References 57 publications

MQANet: Multi-Task Quadruple Attention Network of Multi-Object Semantic Segmentation from Remote Sensing Images

MQANet: Multi-Task Quadruple Attention Network of Multi-Object Semantic Segmentation from Remote Sensing Images

Building Change Detection by W-Shape Resunet++ Network With Triple Attention Mechanism

DD-Net: A Dual Detector Network for Multilevel Object Detection in Remote-Sensing Images

Contact Info

Product

Resources

About