Dual Attention Mechanism Research Articles

Quality assessment of abdominal CT images: an improved ResNet algorithm with dual-attention mechanism.

To enhance medical image classification using a Dual-attention ResNet model and investigate the impact of attention mechanisms on model performance in a clinical setting. We utilized a dataset of medical images and implemented a Dual-attention ResNet model, integrating self-attention and spatial attention mechanisms. The model was trained and evaluated using binary and five-level quality classification tasks, leveraging standard evaluation metrics. Our findings demonstrated substantial performance improvements with the Dual-attention ResNet model in both classification tasks. In the binary classification task, the model achieved an accuracy of 0.940, outperforming the conventional ResNet model. Similarly, in the five-level quality classification task, the Dual-attention ResNet model attained an accuracy of 0.757, highlighting its efficacy in capturing nuanced distinctions in image quality. The integration of attention mechanisms within the ResNet model resulted in significant performance enhancements, showcasing its potential for improving medical image classification tasks. These results underscore the promising role of attention mechanisms in facilitating more accurate and discriminative analysis of medical images, thus holding substantial promise for clinical applications in radiology and diagnostics.

A Practical Study on the Teaching Reform of Civic and Political Integration of Economics Courses in Colleges and Universities Supported by Information Technology

Abstract The issue of strengthening the construction of economics courses, enhancing the moral development of economics professionals, and cultivating professionals with firm and lofty economics ideals is of utmost urgency. In this paper, we model the potential relationship prediction and global correspondence of economics curriculum civics in colleges and universities and then use the sequence markers specific to the subset of relationships to deal with the overlap between entities and entities to complete the ternary extraction work and to realize the joint curriculum civics element entity relationship extraction. Fusion of entity attributes and structural features can be achieved by utilizing the dual attention mechanism, and hyperbolic spatial embedding in graph structure feature extraction can be utilized for entity alignment. The economics program at a university in Guangzhou implements classroom civics integration teaching reform after completing the named entity recognition task test on the dataset. It was found that compared to LEBRT, the current state-of-the-art method for incorporating lexicon information, the model in this paper achieved a performance improvement of 2.53%, 2.26%, and 3.47% in the three metrics, respectively. After one semester of teaching reform and model application, the four scores of Economics Interest, Economics Habit, Economics Confidence, and Economics Autonomous Learning Ability increased by 28.13, 28.65, 18.39, and 26.68 points, respectively, compared with the pre-test, and professionalism also improved by more than 10 points in all cases. This paper provides a useful exploration for optimizing classroom civics teaching methods and efficiency, as well as combining implicit civics with cutting-edge information technology.

Feature Identification and Pedagogical Innovation of English Speaking Teaching in Colleges and Universities Based on Deep Coding Attention

Abstract At present, most students in colleges and universities still have different degrees of difficulty in English oral expression. This study tries to apply deep coding attention to the teaching of spoken English in colleges and universities, taking into account the characteristics of tight time, long cycles, and challenging training in spoken English teaching. By proposing the CIASC-BiLSTM model that integrates the deep coding attention mechanism using a cross-fertilization layer, the attention mechanisms of intention recognition and semantic slot filling introduce explicit associative supplementary information to each other. The ASPAN dual attention mechanism model is employed to learn adversarial training from two public benchmark corpora. To verify the effectiveness of the innovative teaching model of spoken English in colleges and universities based on deep encoding attention, this paper explores the changes in students’ spoken English proficiency through teaching experiments. The results show that the significant difference value between the experimental class and the control class in the posttest of speaking performance is 0.026<0.05, and the experimental class has a substantial improvement over the control class. The results of the pre and post-test t-tests of speaking ability in each dimension of the experimental class are less than 0.05, and the innovative teaching of speaking based on deep coding attention has achieved good results.

Joint Dual Attention Mechanism and Bidirectional Feature Pyramid for Remote Sensing Small Targets Detection

Joint Dual Attention Mechanism and Bidirectional Feature Pyramid for Remote Sensing Small Targets Detection

Joint Dual Attention Mechanism and Bidirectional Feature Pyramid for Remote Sensing Small Targets Detection

Joint Dual Attention Mechanism and Bidirectional Feature Pyramid for Remote Sensing Small Targets Detection

OVANet: Dual Attention Mechanism Based New Deep Learning Framework for Diagnosis and Classification of Ovarian Cancer Subtypes From Histopathological Images

OVANet: Dual Attention Mechanism Based New Deep Learning Framework for Diagnosis and Classification of Ovarian Cancer Subtypes From Histopathological Images

A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning into UNet++ for Remote Sensing Image Coastline Extraction

A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning into UNet++ for Remote Sensing Image Coastline Extraction

Dual-Attention Based Multi-Path Approach for Intensifying Stock Market Forecasting

In light of the existing challenges in capturing short-term fluctuations and achieving accurate predictions in stock market time series data, this research presents the “Dual-Attention MDWT-CVT-LSTM,” a revolutionary financial time series forecasting model. This model makes use of a dual-attention mechanism in conjunction with a Variant Transformation-Gated Long Short-Term Memory (LSTM) network. The approach relies on the Multilevel Discrete Wavelet Transform (MDWT) to separate stock market index sequences into high-frequency and low-frequency components. Furthermore, a transformative gating mechanism is incorporated into the LSTM, featuring fusion gated units to create the VT-LSTM, effectively addressing abrupt short-term information changes. Within the dual-attention network, VT-LSTM is combined with one-dimensional temporal convolution (Conv1D) to extract spatial and temporal features of data at different frequencies. This facilitates the prediction of various sub-sequences, enabling multilevel and multi-path forecasting research. The experimental evaluation uses diverse models on stock market index datasets and individual stock datasets. The results show the superior prediction accuracy of the proposed model compared to alternative methods, underscoring its practical viability in stock market forecasting applications.

A dual attention mechanism network with self-attention and frequency channel attention for intelligent diagnosis of multiple rolling bearing fault types

Different fault types of rolling bearings correspond to different features, and classical deep learning models using a single attention mechanism (AM) have limitations in capturing feature diversity. Therefore, a novel dual attention mechanism network (DAMN) with self-attention (SA) and frequency channel attention (FCA) is proposed for rolling bearing fault diagnosis. The SA mechanism is used to capture global relationships between the input features and fault types, and the FCA mechanism applies multi-spectral attention to learn the local useful information among different input channels. The results of the ablation study on the effects of FCA blocks showed that including a proper combination of multiple frequency components is helpful in achieving higher accuracy. Experiments were conducted to diagnose rolling bearings with multiple types of faults. The results show that, compared with current fault diagnosis models, the proposed DAMN has better comprehensive performance in terms of diagnosis accuracy and model convergence speed. It was also demonstrated that the backbone of DAMN based on a dual AM could achieve better performance than the backbone based on a single AM.

Enhancing traffic signal control with composite deep intelligence

Traffic signal control has always been a hot topic in the field of intelligent transportation. With the increasing complexity of urban traffic conditions due to urbanization, how to develop effective scheduling strategies to adapt to the changing traffic demands has become a key problem in current intelligent transportation. In light of this, this paper focuses on the traffic signal control problem at intersections and proposes a composite intelligent traffic signal control model based on heterogeneous graph neural networks with dual attention mechanisms and deep reinforcement learning. For the first time, the model incorporates the dual attention mechanism in graph neural networks into the traffic signal control, integrating graph neural networks with deep reinforcement learning techniques and traffic intersection scenarios. This allows for the construction of traffic condition models and the scheduling control of traffic resources, catering to the perception and decision-making needs in complex traffic environments. Firstly, the graph relationship representation of intersection resources is established, constructing the graph information structure for traffic flow and signal states. Then, a heterogeneous graph neural network is designed, incorporating both node-level and semantic-level dual attention mechanisms to characterize the traffic state and explore the relationships, enabling the extraction of explicit and implicit information in traffic intersections. Lastly, a deep reinforcement learning algorithm that combines Double Deep Q-Network (DDQN) and Dueling DQN is implemented to improve the algorithm's generalization and execution efficiency, enhancing the adaptability and stability of traffic signal scheduling in complex environments. Simulation tests are conducted on the SUMO simulation platform using real-world application datasets. Compared to four other similar traffic control model, the proposed model demonstrates performance advantages of more than 13% in terms of average reward, average delay, queue length, and waiting time. This validates the effectiveness of the proposed model.

Health-aware food recommendation system with dual attention in heterogeneous graphs

Recommender systems (RS) have been increasingly applied to food and health. However, challenges still remain, including the effective incorporation of heterogeneous information and the discovery of meaningful relationships among entities in the context of food and health recommendations. To address these challenges, we propose a novel framework, the Health-aware Food Recommendation System with Dual Attention in Heterogeneous Graphs (HFRS-DA), for unsupervised representation learning on heterogeneous graph-structured data. HFRS-DA utilizes an attention technique to reconstruct node features and edges and employs a dual hierarchical attention mechanism for enhanced unsupervised learning of attributed graph representations. HFRS-DA addresses the challenge of effectively leveraging the heterogeneous information in the graph and discovering meaningful semantic relationships between entities. The framework analyses recipe components and their neighbours in the heterogeneous graph and can discover popular and healthy recipes, thereby promoting healthy eating habits. We compare HFRS-DA using the Allrecipes dataset and find that it outperforms all the related methods from the literature. Our study demonstrates that HFRS-DA enhances the unsupervised learning of attributed graph representations, which is important in scenarios where labelled data is scarce or unavailable. HFRS-DA can generate node embeddings for unused data effectively, enabling both inductive and transductive learning.

Photovoltaic power forecasting: A dual-attention gated recurrent unit framework incorporating weather clustering and transfer learning strategy

Accurate forecasting of photovoltaic power is essential in the integration, operation, and scheduling of hybrid energy systems. However, modeling for newly built photovoltaic sites is restricted by insufficient training data and computational burden. In this study, a weather clustering-based photovoltaic power forecasting framework incorporating attention mechanism and transfer learning strategy is proposed. By clustering historical days into multiple weather types, the gated recurrent unit-based encoder-decoders with dual-attention mechanism are designed to predict the photovoltaic power generations. The input attention and temporal attention mechanism are responsible for rebuilding input variables and context vectors of the encoder-decoder structure, respectively. Furthermore, a knowledge-transferring strategy, which focuses on establishing an alignment mapping module between the pre-trained structure and the target domain data, is designed for overcoming insufficient data of newly built sites. The data from the actual photovoltaic system are acquired to validate the proposed framework. The proposed forecasting model presents superior performance than other benchmark models, and the knowledge-transferring strategy not only addresses data shortage but also significantly accelerates the training process. With the introduction of knowledge-transferring, the maximum improvement in forecasting accuracy and training efficiency reaches 67.40% and 59.10%.

Dual contrast attention-guided multi-frequency fusion for multi-contrast MRI super-resolution

Objective. Multi-contrast magnetic resonance (MR) imaging super-resolution (SR) reconstruction is an effective solution for acquiring high-resolution MR images. It utilizes anatomical information from auxiliary contrast images to improve the quality of the target contrast images. However, existing studies have simply explored the relationships between auxiliary contrast and target contrast images but did not fully consider different anatomical information contained in multi-contrast images, resulting in texture details and artifacts unrelated to the target contrast images. Approach. To address these issues, we propose a dual contrast attention-guided multi-frequency fusion (DCAMF) network to reconstruct SR MR images from low-resolution MR images, which adaptively captures relevant anatomical information and processes the texture details and low-frequency information from multi-contrast images in parallel. Specifically, after the feature extraction, a feature selection module based on a dual contrast attention mechanism is proposed to focus on the texture details of the auxiliary contrast images and the low-frequency features of the target contrast images. Then, based on the characteristics of the selected features, a high- and low-frequency fusion decoder is constructed to fuse these features. In addition, a texture-enhancing module is embedded in the high-frequency fusion decoder, to highlight and refine the texture details of the auxiliary contrast and target contrast images. Finally, the high- and low-frequency fusion process is constrained by integrating a deeply-supervised mechanism into the DCAMF network. Main results. The experimental results show that the DCAMF outperforms other state-of-the-art methods. The peak signal-to-noise ratio and structural similarity of DCAMF are 39.02 dB and 0.9771 on the IXI dataset and 37.59 dB and 0.9770 on the BraTS2018 dataset, respectively. The image recovery is further validated in segmentation tasks. Significance. Our proposed SR model can enhance the quality of MR images. The results of the SR study provide a reliable basis for clinical diagnosis and subsequent image-guided treatment.

Wear depth estimation from single 2-D image based on shape from Shading and convolutional neural network hybrid model for in-situ wear assessment

Vision-based wear inspection is a prevalent technique in in-situ assessment, such as borescope inspection. Evaluating wear volume of the damage has relied on Shape From Shading (SFS) algorithms to reconstruct the 3-D topography from a single 2-D image. However, this approach faces limitations in accuracy due to data insufficiency and the impact of non-Lambertian reflections on a 2-D surface image. To address this issue, a depth estimation method is proposed, centered on an SFS-Convolutional Neural Network (CNN) hybrid model. First, in terms of the insufficient information of a 2-D image, a coarse-to-fine detection network has been developed to identify the damage region. Regarding the influence of the non-Lambert reflection of the worn surface, an SFS-CNN hybrid model is constructed incorporating an SFS-based guidance branch and a CNN branch based on a dual-attention mechanism. Specifically, the latter emphasizes the connection between the 2-D damage image and the depth information, disregarding non-Lambertian reflection, while the former extracts the initial depth information from the damage region for CNN learning. Consequently, the wear volume can be derived by accumulating the depth of the reconstructed 3-D worn region. To verify, several real worn surfaces have been used and examined using the proposed model and Laser Scanning Confocal Microscopy. Experimental results indicate that the proposed method can determine the depth of a worn surface from a single surface image, and the absolute relative error of the computed wear volume is less than 19 %, which satisfies the requirement of in-situ wear condition assessment.

BGSNet: A cascaded framework of boundary guided semantic for COVID-19 infection segmentation

Coronavirus disease 2019 (COVID-19) has spread globally in early 2020, leading to a new health crisis. Automatic segmentation of lung infections from computed tomography (CT) images provides an important basis for rapid diagnosis of COVID-19. This paper proposes a cascaded architecture of boundary guided semantic network (BGSNet) based on boundary supervision, multi-scale atrous convolution and dual attention mechanism. The BGSNet cascaded architecture includes a boundary supervision module (BSM), a multi-scale atrous convolution module (MACM), and a dual attention guidance module (DAGM). BSM provides boundary supervised features through explicit modeling to guide precise localization of target regions. MACM introduces atrous convolution with different dilation rates to obtain multi-scale receptive field, thus enhancing the segmentation ability of targets with different scales. DAGM combines channel and spatial attention to filter irrelevant information and enhance feature learning ability. The experimental results based on publicly available CO-Seg and CLSC datasets show that the BGSNet cascaded architecture achieves DSC of 0.806 and 0.677, respectively, which is superior to the advanced COVID-19 infection segmentation model. The effectiveness of the main components of BGSNet has been demonstrated through ablation experiments.

OMOFuse: An Optimized Dual-Attention Mechanism Model for Infrared and Visible Image Fusion

Infrared and visible image fusion aims to fuse the thermal information of infrared images and the texture information of visible images into images that are more in compliance with people’s visual perception characteristics. However, in the existing related work, the fused images have incomplete contextual information and poor fusion results. This paper presents a new image fusion algorithm—OMOFuse. At first, both the channel and spatial attention mechanisms are optimized by a DCA (dual-channel attention) mechanism and an ESA (enhanced spatial attention) mechanism. Then, an ODAM (optimized dual-attention mechanism) module is constructed to further improve the integration effect. Moreover, a MO module is used to improve the network’s feature extraction capability for contextual information. Finally, there is the loss function ℒ from the three parts of SSL (structural similarity loss), PL (perceptual loss), and GL (gap loss). Extensive experiments on three major datasets are performed to demonstrate that OMOFuse outperforms the existing image fusion methods in terms of quantitative determination, qualitative detection, and superior generalization capabilities. Further evidence of the effectiveness of our algorithm in this study are provided.

High-throughput soybean pods high-quality segmentation and seed-per-pod estimation for soybean plant breeding

Accurately identifying soybean pods is a crucial prerequisite for retrieving multi-phenotypic traits (such as number of pods per plant, number of seeds per pod, pod size, pod color, and pod shape). However, the traditional manual measurement approach for pod phenotype investigation is time-consuming and labor-intensive, particularly when counting the number of seeds per pod. Furthermore, existing instance segmentation methods designed for coarse-grained classification are inadequate for precise seed-per-pod estimation. To address these challenges, we modified an instance segmentation network for high-throughput soybean pods high-quality segmentation and accurate seed-per-pod estimation. We modified the classification branch of the instance segmentation network Mask Transfiner (Ke et al., 2022) by increasing the resolution of feature map of each Region of Interest (RoI) region, incorporating a dual attention mechanism, and leveraging a center loss function, named RefinePod. To overcome the limitation of scarce labeled data, we modified our synthesizing image method to automatedly generate fine-labeled multi-class soybean pods images. We then train RefinePod purely with these synthetic images. Subsequently, we evaluate the trained model on both synthetic and real test images. Experimental results demonstrate a significant improvement in the accuracy of seed-per-pod estimation achieved by RefinePod. Additionally, we conduct ablation experiments to analyze the individual contributions of each strategy employed in RefinePod. In summary, RefinePod achieves remarkable results in seed-per-pod estimation accuracy by integrating advanced techniques and leveraging synthetic images for training. Our findings highlight the potential of RefinePod for accelerating soybean phenotype investigation, enabling more efficient agricultural research and crop improvement initiatives.

Learning Degradation-Robust Spatiotemporal Frequency-Transformer for Video Super-Resolution.

Video Super-Resolution (VSR) aims to restore high-resolution (HR) videos from low-resolution (LR) videos. Existing VSR techniques usually recover HR frames by extracting pertinent textures from nearby frames with known degradation processes. Despite significant progress, grand challenges remain to effectively extract and transmit high-quality textures from high-degraded low-quality sequences, such as blur, additive noises, and compression artifacts. This work proposes a novel degradation-robust Frequency-Transformer (FTVSR++) for handling low-quality videos that carry out self-attention in a combined space-time-frequency domain. First, video frames are split into patches and each patch is transformed into spectral maps in which each channel represents a frequency band. It permits a fine-grained self-attention on each frequency band so that real visual texture can be distinguished from artifacts. Second, a novel dual frequency attention (DFA) mechanism is proposed to capture the global and local frequency relations, which can handle different complicated degradation processes in real-world scenarios. Third, we explore different self-attention schemes for video processing in the frequency domain and discover that a "divided attention" which conducts joint space-frequency attention before applying temporal-frequency attention, leads to the best video enhancement quality. Extensive experiments on three widely-used VSR datasets show that FTVSR++ outperforms state-of-the-art methods on different low-quality videos with clear visual margins. Code and pre-trained models are available at https://github.com/researchmm/FTVSR.

Enhancing coal-gangue object detection using GAN-based data augmentation strategy with dual attention mechanism

Coal separation based on computer vision has attracted substantial attention in recent years. However, developing reliable object detection models relies on large-scale annotated dataset, which in industrial practice is time-consuming and labor-intensive to obtain. In this paper, we propose a novel data augmentation model called dual attention deep convolutional generative adversarial network (DADCGAN) to expand dataset scale and improve object detection. For the first time, the proposed DADCGAN, which adopts DCGAN as its foundation architecture, introduces efficient channel attention and external attention mechanisms to capture essential feature information from the channel and spatial dimensions of images, respectively. Moreover, spectral normalization and two time-scale update rule strategies are incorporated to stabilize the training process. The implementation of our proposed data augmentation strategy includes two steps. First, traditional pixel transformation is used to expand an original small dataset. Then, our GAN-based data augmentation is executed to further expand the dataset by generating synthetic images. Experimental results show that our DADCGAN model achieves the lowest FID value, decreasing the FID by 21.30–71.96 % compared to other baseline GAN models, showcasing its ability to produce more realistic coal-gangue images. Finally, the data augmentation strategies are applied to the YOLOv4 model, enhancing the mAP by 9.26 %, highlighting its significance in enhancing coal-gangue object detection. These results have important implications for the development and implementation of computer vision-based technologies, enabling the realization of cleaner and more efficient coal separation methods.

Innovative Dual-Stage Blind Noise Reduction in Real-World Images Using Multi-Scale Convolutions and Dual Attention Mechanisms

The distribution of real noise in images can disrupt the inherent symmetry present in many natural visuals, thus making its effective removal a paramount challenge. However, traditional denoising methods often require tedious manual parameter tuning, and a significant portion of deep learning-driven techniques have proven inadequate for real noise. Moreover, the efficiency of end-to-end algorithms in restoring symmetrical patterns in noisy images remains questionable. To harness the principles of symmetry for improved denoising, we introduce a dual deep learning model with a focus on preserving and leveraging symmetrical patterns in real images. Our methodology operates in two stages. In the first, we estimate the noise level using a four-layer neural network, thereby aiming to capture the underlying symmetrical structures of the original image. To enhance the extraction of symmetrical features and overall network performance, a dual attention mechanism is employed before the final convolutional layer. This innovative module adaptively assigns weights to features across different channels, thus emphasizing symmetry-preserving elements. The subsequent phase is devoted to non-blind denoising. It integrates the estimated noise level and the original image, thus targeting the challenge of denoising while preserving symmetrical patterns. Here, a multi-scale architecture is used, thereby amalgamating image features into two branches. The first branch taps into dilation convolution, thus amplifying the receptive field without introducing new parameters and making it particularly adept at capturing broad symmetrical structures. In contrast, the second branch employs a standard convolutional layer to focus on finer symmetrical details. By harnessing varied receptive fields, our method can recognize and restore image symmetries across different scales. Crucial skip connections are embedded within this multi-scale setup, thus ensuring that symmetrical image data is retained as the network deepens. Experimental evaluations, conducted on four benchmark training sets and 12 test datasets, juxtaposed with over 20 contemporary models based on the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics, underscore our model’s prowess in not only denoising but also in preserving and accentuating symmetrical elements, thereby setting a new gold standard in the field.