Convolutional block attention module U-Net: a method to improve attention mechanism and U-Net for remote sensing images

Zhang, Yanjun; Kong, Jiayuan; Long, Sifang; Zhu, Yuanhao; He, Fushuai

doi:10.1117/1.jrs.16.026516

Cited by 10 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As stated earlier, the segmentation models are UNet models with VGG-16 as a backbone of the encoder. Along with vanilla UNet, this study considers three variants of UNet : UNet-CBAM [37], UNet-SE [37], and UNet-(CBAM+SE) [37] obtained with three attention mechanism CBAM [38], SE [39], and CBAM+SE [37], respectively. The experimental setup of the segmentation and classification model for the two tiers are provided below:…”

Section: Segmentation and Classification Modelsmentioning

confidence: 99%

Integrated Document Segmentation and Region Identification- Textual, Equation and Graphical

Thiyam

Singh

Kumar

2023

Preprint

View full text Add to dashboard Cite

With the advancement in the world of digitization, storing information in the form of scanned copies, images, etc. becomes a new normal. This new normal leads to the need for a system that can extract accurate information from the scanned documents or images with respect to every component they may have, such as textual, graphical, etc. The first step in extracting document information is to segment the document layout: divide the document into textual and non-textual regions of interest. There have been various studies over document layout segmentation, and this study observed that the majority of the existing studies face one common challenge, i.e., accurate segmentation of graphical components with sparsely clustered pixels such as flowcharts, block diagrams, etc. The study addresses it with a two-tier feedback-based framework. The first tier segments and classifies the textual and mathematical equation components, while the second tier segments and classifies the graphical regions using the feedback information from the first tier. The information provided by the first tier is the regional information of the equation and textual components to get a different copy of the original input document image in such a way that most of the foreground pix-els are part of graphical regions. The proposed framework outperforms various existing studies (when evaluated against multiple datasets).

show abstract

Section: Segmentation and Classification Modelsmentioning

confidence: 99%

Integrated Document Segmentation and Region Identification- Textual, Equation and Graphical

Thiyam

Singh

Kumar

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The input feature map is first handled separately by MaxPool3D and AvgPool3D based on height, width and depth, then entered into a multi-layer perceptron (MLP) 15 . The features output by MLP are subjected to elementwise addition and sigmoid activation operations to produce channel attention feature maps.…”

Section: Learning the Temporal-spatial Feature Through 3d-ts Attentionmentioning

confidence: 99%

“…where W denotes the weight matrix, b denotes the bias term, and σ represents the sigmoid activation function 15 .…”

Section: Learning Temporal Features Of Tc's Evolution Process Through...mentioning

confidence: 99%

Three-dimensional temporal-spatial attention for tropical cyclone forecast

Lin,

Jin,

Lin

et al. 2023

Fourth International Conference on Computer Science and Communication Technology (ICCSCT 2023)

View full text Add to dashboard Cite

The tropical cyclone (TC) is a strong and highly destructive tropical low-pressure vortex that often brings disasters such as strong wind, heavy rain, and storm surge. The formation and intensity forecast of TC is very important for TC disaster warnings. In this paper, we propose a three-dimensional temporal-spatial (3D-TS) attention TC forecast model based on deep learning, which considers the temporal-spatial relationship between TC variables on the basis of machine learning methods. The model introduces 2D convolutional neural networks (2DCNNs) and 3D convolutional neural networks (3DCNNs) to learn oceanographic variables and atmospheric variables of TC, while utilizing Long Short-Term Memory (LSTM) for capturing the temporal correlation in TC’s evolution process, and introduces 3D-TS to grasp the temporalspatial characteristic of TC and enhance the model’s precision. Through experiments, it was found that the model’s performance in TC formation and intensity forecast is better than many existing numerical forecasting methods, statistical forecasting methods, and machine learning methods. We validated the model on the Western Pacific TC dataset, in the TC formation forecast experiment, the model can achieve a maximum accuracy rate of 86.1% and an AUC value of 92.5%. In the TC intensity forecast experiment, the minimum error is 7.1 kt, showing that we achieved state-of-the-art results.

show abstract

“…Kong and Zhang [17][18] proposed the parallel attention mechanism module, also known as ProCBAM, in remote sensing scene classification. Fig.…”

Section: Procbam Attention Mechanism Structurementioning

confidence: 99%

“…Fig. 5 depicts the structural movement and basic configuration of the ProCBAM attention technique that was suggested in this work [17][18]. The attention mechanism and its numerous modules including the CAM (i.e.…”

Section: Procbam Attention Mechanism Structurementioning

confidence: 99%

DU-Net-Cloud: A Smart Cloud-Edge Application with an Attention Mechanism and U-Net for Remote Sensing Images and Processing

Kong

Zhang

2022

Preprint

View full text Add to dashboard Cite

In recent ages, the use of deep learning approaches to extract ground object information from remote sensing high-resolution images has attracted extensive attention in many fields. Nevertheless, due to the high similarity of features between roads, prevailing deep learning semantic segmentation networks commonly demonstrate reduced continuity in road segmentation. In order to better study the road details in images related to remote sensing, this paper suggests a road extraction technique which is founded on Dimensional U-Net (DU-Net) network. At the deepening level of U-Net network, a parallel attention mechanism, known as ProCBAM, is added and implemented to the feature transmission step of the U-Net network. Moreover, we use the edge-cloud architecture to develop and construct a unique remote sensing image service system that integrates several datacenters and their related edge infrastructure. The edge network is primarily used for caching and distributing the processed remote sensing images, while the remote datacenter serves as the cloud platform and is responsible for the storage and processing of original remote sensing images. The results show that DU-Net has good performance in road segmentation and can achieve improved road segmentation and resolve the issue of reduced continuity of road segmentation when compared with other state-of-the-art learning networks. We observed that the proposed system not only distributes the workload of processing tasks across the edges but also achieves data efficiency among them, which enhances image processing efficiency and lowers data transmission costs.

show abstract

Convolutional block attention module U-Net: a method to improve attention mechanism and U-Net for remote sensing images

Cited by 10 publications

References 20 publications

Integrated Document Segmentation and Region Identification- Textual, Equation and Graphical

Integrated Document Segmentation and Region Identification- Textual, Equation and Graphical

Three-dimensional temporal-spatial attention for tropical cyclone forecast

DU-Net-Cloud: A Smart Cloud-Edge Application with an Attention Mechanism and U-Net for Remote Sensing Images and Processing

Contact Info

Product

Resources

About