Channel Attention Module Research Articles

EfficientUNet: An efficient solution for breast tumour segmentation in ultrasound images

AbstractThe accurate segmentation of breast tumours is important for the diagnosis and treatment of breast cancer. When using the classic U‐Net, Attention‐UNet, and UNet++ to segment the tumour, there are problems of oversegmentation, incorrect segmentation, and poor edge continuity. In this paper, an effective tumour segmentation method, EfficientUNet, is proposed. EfficientUNet adopts a step‐by‐step enhancement method, combining ResNet18, a channel attention mechanism and deep supervision. ResNet18, as the encoder of the whole network, solves the problem of gradient disappearanceand improves the feature extraction ability of the model. The channel attention module makes the model more accurate in tumour edge processing. The deep supervision technology accelerates the model training and provides the convergence direction for the model. In addition, it is found that when adjusting the size of the image, the method of image filling before clipping (or zooming) is more conducive to model learning than the direct interpolation method. And a comparative experiment wasperformed on dataset B. Compared to U‐Net, Attention‐UNet and UNet++, EfficientUNet has the highest performance. Finally, the ablation experiment also indicated the effectiveness of each module in EfficientUNet.

Sequence signal reconstruction based multi-task deep learning for sleep staging on single-channel EEG

The temporal context information between sleep stage sequence contains sleep transition rules, which is important for improving sleep staging performance. Existing multi-task learning methods reconstruct EEG signals from one sleep stage, ignoring the importance of sequential temporal context in capturing long-term dependencies to enhance representation learning. To address these issues, we propose a multi-task deep learning model to jointly reconstruct sequence signal and segment time series. The model enhances the ability of time series segmentation task to capture sequential temporal context and improves the performance of single-channel EEG by optimizing the common encoder for sequence signal reconstruction task. In addition, we design a one-dimensional channel attention module to enhance the feature representation extracted for sleep sequence signal. The experimental results on four datasets show that the multi-task deep learning model can improve the generalization using sequence signal reconstruction. Compared with other state-of-the-art methods, the method proposed in this study obtained competitive performance in terms of metrics such as accuracy, which is 85.6% on the 2013 version of Sleep-EDF Database Expanded, 83.4% on the 2018 version of Sleep-EDF Database Expanded, 85.6% on Sleep Heart Health Study, and 77.4% on CAP Sleep Database.

EAMNet: an Alzheimer’s disease prediction model based on representation learning

Objective. Brain 18F-FDG PET images indicate brain lesions’ metabolic status and offer the predictive potential for Alzheimer’s disease (AD). However, the complexity of extracting relevant lesion features and dealing with extraneous information in PET images poses challenges for accurate prediction. Approach. To address these issues, we propose an innovative solution called the efficient adaptive multiscale network (EAMNet) for predicting potential patient populations using positron emission tomography (PET) image slices, enabling effective intervention and treatment. Firstly, we introduce an efficient convolutional strategy to enhance the receptive field of PET images during the feature learning process, avoiding excessive extraction of fine tissue features by deep-level networks while reducing the model’s computational complexity. Secondly, we construct a channel attention module that enables the prediction model to adaptively allocate weights between different channels, compensating for the spatial noise in PET images’ impact on classification. Finally, we use skip connections to merge features from different-scale lesion information. Through visual analysis, the network constructed in this article aligns with the regions of interest of clinical doctors. Main results. Through visualization analysis, our network aligns with regions of interest identified by clinical doctors. Experimental evaluations conducted on the ADNI (Alzheimer’s Disease Neuroimaging Initiative) dataset demonstrate the outstanding classification performance of our proposed method. The accuracy rates for AD versus NC (Normal Controls), AD versus MCI (Mild Cognitive Impairment), MCI versus NC, and AD versus MCI versus NC classifications achieve 97.66%, 96.32%, 95.23%, and 95.68%, respectively. Significance. The proposed method surpasses advanced algorithms in the field, providing a hopeful advancement in accurately predicting and classifying Alzheimer’s Disease using 18F-FDG PET images. The source code has been uploaded to https://github.com/Haoliang-D-AHU/EAMNet/tree/master.

A learnable EEG channel selection method for MI-BCI using efficient channel attention.

During electroencephalography (EEG)-based motor imagery-brain-computer interfaces (MI-BCIs) task, a large number of electrodes are commonly used, and consume much computational resources. Therefore, channel selection is crucial while ensuring classification accuracy. This paper proposes a channel selection method by integrating the efficient channel attention (ECA) module with a convolutional neural network (CNN). During model training process, the ECA module automatically assigns the channel weights by evaluating the relative importance for BCI classification accuracy of every channel. Then a ranking of EEG channel importance can be established so as to select an appropriate number of channels to form a channel subset from the ranking. In this paper, the ECA module is embedded into a commonly used network for MI, and comparative experiments are conducted on the BCI Competition IV dataset 2a. The proposed method achieved an average accuracy of 75.76% with all 22 channels and 69.52% with eight channels in a four-class classification task, outperforming other state-of-the-art EEG channel selection methods. The result demonstrates that the proposed method provides an effective channel selection approach for EEG-based MI-BCI.

Siamese Visual Tracking with Spatial-Channel Attention and Ranking Head Network

Trackers based on the Siamese network have received much attention in recent years, owing to its remarkable performance, and the task of object tracking is to predict the location of the target in current frame. However, during the tracking process, distractors with similar appearances affect the judgment of the tracker and lead to tracking failure. In order to solve this problem, we propose a Siamese visual tracker with spatial-channel attention and a ranking head network. Firstly, we propose a Spatial Channel Attention Module, which fuses the features of the template and the search region by capturing both the spatial and the channel information simultaneously, allowing the tracker to recognize the target to be tracked from the background. Secondly, we design a ranking head network. By introducing joint ranking loss terms including classification ranking loss and confidence&IoU ranking loss, classification and regression branches are linked to refine the tracking results. Through the mutual guidance between the classification confidence score and IoU, a better positioning regression box is selected to improve the performance of the tracker. To better demonstrate that our proposed method is effective, we test the proposed tracker on the OTB100, VOT2016, VOT2018, UAV123, and GOT-10k testing datasets. On OTB100, the precision and success rate of our tracker are 0.925 and 0.700, respectively. Considering accuracy and speed, our method, overall, achieves state-of-the-art performance.

Multiencoder‐based federated intelligent deep learning model for brain tumor segmentation

AbstractGlioma, a primary tumor derived from brain glial cells, is around 45% of all intracranial tumors. Magnetic resonance imaging's (MRI's) precise glioma segmentation is crucial for clinical purposes. This article presents a novel automatic brain tumor segmentation approach based on a multi‐encoder‐based federated intelligent deep learning framework. The suggested method uses a U‐shaped network design that multiplies the single contraction path into several paths to explore semantic information modalities deeply. The basic convolutional layer uses an Inception module and dilated convolutions to extract multi‐scale features from the images using artificial intelligent. To emphasize segmentation‐related information while ignoring redundant channel dimension information and improving the accuracy of network segmentation, lightweight channel attention efficient channel attention (ECA) modules are inserted into the bottleneck layer and decoder. The collection of data for the 2018 Brain Tumor Segmentation Challenge (BraTS 2018) is used to test the effectiveness of the suggested structure, and the findings indicate that the growth core, for the entire tumor and the augmented tumor regions, respectively, the average Dice coefficients are 0.880, 0.784, and 0.757. These findings support the proposed algorithm's ability to accurately and successfully segregate multimodal MRI brain tumors.

Research on None-Line-of-Sight/Line-of-Sight Identification Method Based on Convolutional Neural Network-Channel Attention Module.

None-Line-of-Sight (NLOS) propagation of Ultra-Wideband (UWB) signals leads to a decrease in the reliability of positioning accuracy. Therefore, it is essential to identify the channel environment prior to localization to preserve the high-accuracy Line-of-Sight (LOS) ranging results and correct or reject the NLOS ranging results with positive bias. Aiming at the problem of the low accuracy and poor generalization ability of NLOS/LOS identification methods based on Channel Impulse Response (CIR) at present, the multilayer Convolutional Neural Networks (CNN) combined with Channel Attention Module (CAM) for NLOS/LOS identification method is proposed. Firstly, the CAM is embedded in the multilayer CNN to extract the time-domain data features of the original CIR. Then, the global average pooling layer is used to replace the fully connected layer for feature integration and classification output. In addition, the public dataset from the European Horizon 2020 Programme project eWINE is used to perform comparative experiments with different structural models and different identification methods. The results show that the proposed CNN-CAM model has a LOS recall of 92.29%, NLOS recall of 87.71%, accuracy of 90.00%, and F1-score of 90.22%. Compared with the current relatively advanced technology, it has better performance advantages.

Augmenting Beam Alignment for mmWave Communication Systems via Channel Attention

The beamforming technique has attracted considerable attention in wireless communication due to its various advantages such as interference reduction and improved wireless resource efficiency. However, the beam alignment between transmitting and receiving devices, which is fundamentally required for the beamforming, poses a significant challenge due to the continuous variability of the wireless channel. Recently, a deep learning-based technique has been proposed to predict narrow beam indices by measuring wide beams. However, there is room for improvement in the performance of the neural network architecture employed in this technique. Therefore, we suggest a novel deep learning model architecture that incorporates a channel attention module for beam training. The simulation results show a significant enhancement in performance with our scheme compared to both a state-of-the-art approach and other existing methods across all scenarios. Particularly, we confirm that even when reducing the number of wide beams used for measurement by approximately 50%, our proposed approach achieves a performance close to that of the state-of-the-art scheme.

Dual-Metric Neural Network With Attention Guidance for Surface Defect Few-Shot Detection in Smart Manufacturing

Abstract As an important application of human–robot collaboration, intelligent detection of surface defects is crucial for production quality control, which also helps in relieving the workload of technical staff in human-centric smart manufacturing. To accurately detect defects with limited samples in industrial practice, a dual-metric neural network with attention-guided is proposed. First, an attention-guided recognition network with channel attention and position attention module is designed to efficiently learn representative defect features with limited samples. Second, aiming to detect defects with confusing surface images, a dual-metric function is presented to learn the classification boundary by controlling the distance of samples in feature space from intraclass and interclass. The experiment results on the fabric defect dataset demonstrate that the proposed approach outperforms state-of-the-art methods in accuracy, recall, precision, F1-score, and few-shot accuracy. Further comparative experiments reveal that the dual-metric function is superior in improving the few-shot detection accuracy.

Improving defocus blur detection via adaptive supervision prior-tokens

The Defocus Blur Detection (DBD) technique is devised to accurately identify regions of blurriness within images. The prediction difficulty of defocused pixels is closely associated with their spatial location. Owing to the cluttered background, pixels near the edges are more prone to erroneous predictions. To address the issue of uneven pixel distribution at the edges of defocused regions, we deliberately decouple the original labels into Prior-Tokaens: Edge Transition Detail Region (EDR) and Structure Body Region (SBR). Subsequently, we propose a novel adaptive multi-supervised network comprising a feature extraction module, a feature fusion network (FFN), and a Multi-scale Channel Attention Module (MCAM). This method harnesses complementary features between SBR and EDR, furnishing a tailored feature learning strategy that outperforms traditional single-supervised techniques. Furthermore, considering that features generated with varying receptive fields contain information at different levels, we introduce MCAM to identify feature pixels at different scales, enhancing semantic relevance. Moreover, for images with complex scenes, an adaptive learning scheme is developed to selectively fuse low-level detail features and high-level semantic information, thereby enhancing the model's generalization capability. The proposed approach outperforms state-of-the-art techniques on various evaluation metrics, as demonstrated through qualitative and quantitative analyses of popular public datasets.

Simultaneous denoising and reconstruction of distributed acoustic sensing seismic data via a multicascade deep-learning method

Distributed acoustic sensing (DAS) has been moderately used in seismic exploration as a consequence of its advantages, such as low cost, high resolution, high sensitivity, and strong resistance to high temperatures. Nonetheless, seismic data recorded by the DAS system often are seriously contaminated by a massive amount of background noise and recording gaps, which also decrease the quality of DAS seismic data. Building on its success in numerous fields of data processing, convolutional neural networks (CNNs) also have been applied to seismic data denoising as well as reconstruction and achieved good performance compared with traditional methods. However, relatively few CNN-based studies have been done on the simultaneous denoising and reconstruction of seismic data, especially for the complex DAS seismic data with a low signal-to-noise ratio. In this study, we have developed a multicascade network structure in combination with a channel attention mechanism (MCA-Net) to achieve the simultaneous denoising and reconstruction of DAS seismic data by only using a unified trained model. Particularly, our MCA-Net consists of three branches of cascade networks that can extract abundant features from DAS seismic data with different resolutions. Furthermore, we deploy some channel attention modules and aggressive blocks to MCA-Net to fuse these aforementioned multiresolution features and thus improving the feature extraction ability of the whole network. Meanwhile, a high-quality training data set composed of paired clean complete and noisy incomplete patches is used to train MCA-Net in a supervised fashion. Some synthetic and real DAS seismic data are used to demonstrate the effectiveness of MCA-Net, and our method exhibits better denoising and reconstruction performance than some traditional methods and two existing CNN architectures.

Psoriasis severity classification based on adaptive multi-scale features for multi-severity disease

Psoriasis is a skin disease that causes lesions of various sizes across the body and can persist for years with cyclic deterioration and improvement. During treatment, and a multiple-severity disease, with irregular severity within the observation area may be found. The current psoriasis evaluation is based on the subjective evaluation criteria of the clinician using the psoriasis area and severity index (PASI). We proposed a novel psoriasis evaluation method that detects representative regions as evaluation criteria, and extracts severity features to improve the evaluation performance of various types of psoriasis, including multiple-severity diseases. We generated multiple-severity disease images using CutMix and proposed a hierarchical multi-scale deformable attention module (MS-DAM) that can adaptively detect representative regions of irregular and complex patterns in multiple-severity disease analyses. EfficientNet B1 with MS-DAM exhibited the best classification performance with an F1-score of 0.93. Compared with the performance of the six existing self-attention methods, the proposed MS-DAM showed more than 5% higher accuracy than that of multiscale channel attention module (MS-CAM). Using the gradient-weighted activation mapping method, we confirmed that the proposed method works at par with human visual perception. We performed a more objective, effective, and accurate analysis of psoriasis severity using the proposed method.

A new method for safety helmet detection based on convolutional neural network.

Considering practical issues such as cost control of hardware facilities in engineering projects, it is a challenge to design a robust safety helmet detection method, which can be implemented on mobile or embedded devices with limited computing power. This paper presents an approach to optimize the BottleneckCSP structure in the YOLOv5 backbone network, which can greatly reduce the complexity of the model without changing the size of the network input and output. To eliminate the information loss caused by upsampling and enhance the semantic information of the feature map on the reverse path, this paper designs an upsampling feature enhancement module. Besides, To avoid the negative impact of redundant information generated by feature fusion on the detection results, this paper introduces a self-attention mechanism. That is, using the designed channel attention module and location attention module, adjacent shallow feature maps and upsampled feature maps are adaptively fused to generate new feature maps with strong semantics and precise location information. Compared with the existing methods with the fastest inference speed, under the same compute capability, the proposed method not only has faster inference speed, the FPS can reach 416, but also has better performance with mAP of 94.2%.

RC-Net: A region-level context network for hyperreflective dots segmentation in retinal OCT images

Due to chronic exposure to hyperglycemia, the ocular biomechanical homeostasis of diabetics is disturbed, which may cause multiple ocular diseases, such as diabetic retinopathy (DR). In retinal optical coherence tomography (OCT) images of patients with DR, hyperreflective dots (HRDs) are spot-shaped areas with high reflectivity and high local contrast. Quantitative analyses of HRDs are the key to make appropriate decisions on diagnosis and treatment. The small scale, similarity to background and interference of other foci bring great challenges to accurate and automatic segmentation of HRDs. To address above challenges, we propose a novel region-level context network (RC-Net), which introduces region-level position attention module (RPAM) and region-level channel attention module (RCAM) for HRDs segmentation. Four RPAMs are embedded behind ordinary convolution blocks to extract rich contextual dependencies, which help to cluster pixels in same class and reveal differences between HRDs and background. To further improve feature representation, a RCAM is embedded into the top of the encoder structure to adaptively utilize the semantic dependencies between different channels. We evaluate the proposed RC-Net on a dataset, which consists of 450 2D OCT B-scans. The mean and standard deviation of dice similarity coefficient (DSC), intersection over union (IoU), recall (R) and precision (P) are 75.29±0.42%, 62.27±0.54%, 78.36±1.79% and 75.34±0.52%, respectively. The experiments show that the proposed RC-Net achieves superior segmentation performance of HRDs segmentation to state-of-the-art methods.

An improved YOLOv5s model for effectively predict sugarcane seed replenishment positions verified by a field re-seeding robot

Sugarcane field re-seeding robot is a promising yield-enhancing technology proposed to solve the seedling absences in sugarcane fields. In this study, in combination with developing the sugarcane field re-seeding robot, an improved YOLOv5s model was proposed to detect sugarcane seedlings and predict seed replenishment positions. Firstly, field images of one-month-old sugarcane seedlings were taken at different light conditions as a dataset. Secondly, the Slim-Neck was introduced to replace the Neck network, which can reduce the complexity of the model while maintaining sufficient accuracy. Thirdly, the Efficient Channel Attention (ECA) module was added to the Backbone network to enhance the model's attention on critical feature information of sugarcane seedlings. Fourthly, the SCYLLA-IoU (SIoU) loss function was introduced to speed up the convergence of the proposed model. Lastly, a method for predicting seed replenishment positions was proposed and verified by the field tests. The experimental results showed that the mean average precision (mAP), precision, and recall of the improved YOLOv5s model were 93.1 %, 92.1 %, and 89.9 %, respectively, and the detection speed was 82 frames per second (FPS), which increased the mAP by 1.5 % and the detection speed by 12.3 % compared to the original YOLOv5s model. In addition, compared with Faster R-CNN, SSD, and YOLOv4-tiny models, the improved YOLOv5s model had a higher accuracy, faster detection speed, and less memory consumption. The field test showed that the real-time detection speed of the improved YOLOv5s model was 23 FPS in Nvidia Jetson TX2. The real-time detection precision of sugarcane seedlings was 97.2 %, and the recall was 86.7 %. The mean relative error between the numbers of seed replenishment positions predicted by the robot and that predicted by the human was 18.7 %. Consequently, the improved YOLOv5s model can efficiently and accurately detect sugarcane seedlings and predict seed replenishment positions. This technology provides valuable visual detection support for the sugarcane field re-seeding robot.

Research on computer network information image data processing based on machine learning

Abstract In this paper, we aim to progress the efficiency and accuracy of information processing and security detection in computer networks by introducing convolutional neural networks in machine learning algorithms that are capable of multi-scaling from the channel attention module and spatial attention module in extracting image information. Global maximum pooling and global averaging are done for the feature maps generated by both modules to get the clearest feature maps by dimensionality reduction. The loss function is used to calculate the feature maps to reduce the data loss generated during data extraction and finally complete the image data processing. To verify the effectiveness of the proposed platform, network images containing different amounts of data are input into the platform, and the accuracy and loss of data extraction are obtained. The results show that the data extraction accuracy of the reduced platform is up to 100%, which is 6% higher than other platforms. The number of data losses in other platforms is more than twice of this paper, while the number of losses in this paper can be controlled within 5. It can be seen that convolutional neural network in machine learning improves the accuracy of data extraction from computer network information images and reduces the loss in data extraction.

Automated evaluation of retinal hyperreflective foci changes in diabetic macular edema patients before and after intravitreal injection.

Fast and automated reconstruction of retinal hyperreflective foci (HRF) is of great importance for many eye-related disease understanding. In this paper, we introduced a new automated framework, driven by recent advances in deep learning to automatically extract 12 three-dimensional parameters from the segmented hyperreflective foci in optical coherence tomography (OCT). Unlike traditional convolutional neural networks, which struggle with long-range feature correlations, we introduce a spatial and channel attention module within the bottleneck layer, integrated into the nnU-Net architecture. Spatial Attention Block aggregates features across spatial locations to capture related features, while Channel Attention Block heightens channel feature contrasts. The proposed model was trained and tested on 162 retinal OCT volumes of patients with diabetic macular edema (DME), yielding robust segmentation outcomes. We further investigate HRF's potential as a biomarker of DME. Results unveil notable discrepancies in the amount and volume of HRF subtypes. In the whole retinal layer (WR), the mean distance from HRF to the retinal pigmented epithelium was significantly reduced after treatment. In WR, the improvement in central macular thickness resulting from intravitreal injection treatment was positively correlated with the mean distance from HRF subtypes to the fovea. Our study demonstrates the applicability of OCT for automated quantification of retinal HRF in DME patients, offering an objective, quantitative approach for clinical and research applications.

Semantic segmentation of remote sensing images combined with attention mechanism and feature enhancement U-Net

ABSTRACT Target segmentation of remote sensing images has always been a hotspot in image processing. This paper proposes a new semantic segmentation technology for remote sensing images, which uses Unet as the backbone and combines attention mechanism and feature enhancement module. The feature enhancement module can enlarge the information of the region of interest (ROI) to improve the contrast of the image; the attention mechanism includes spatial and channel attention modules, which can obtain more detailed information of the desired target while suppressing other useless information. This paper improves the loss function of the traditional Unet. On the basis of the sparse categorical cross-entropy function, the mean squared logarithmic error function is added, which can effectively improve the accuracy of semantic segmentation. The experimental results show that the algorithm has higher computational accuracy than Unet, DeepLabV3, SegNet, PSPNet, CBAM and DAnet while having the computational speed of FCN and Unet in model testing and validation.

Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring

Recently, due to the rapid development of deep neural networks in the field of computer vision, many studies have been conducted in the field of image deblurring. However, previous methods cannot attain satisfactory deblurring performance in object boundaries and local regions containing image details in restored results. This paper proposes a new method that uses a locally adaptive channel attention module for a spectral–spatial network to resolve the problem of single-image deblurring. Unlike existing methods, our proposed method consists of a spectral restorer and spatial restorer that adopt a locally adaptive attention mechanism in the spectral–spatial domains. In addition, unlike a conventional spectral–spatial network that only considers the magnitude of the frequency coefficients, the proposed method uses both the magnitude and phase of the frequency coefficients in the training stage. Our locally adaptive channel attention spectral–spatial network can focus on informative channels that are closely related to blur artifacts. Specifically, the spatial restorer, which guides the intensity of the blur image to fit the ground truth by exploring the interdependencies of feature channels, can efficiently restore scene characteristics while the spectral restorer, which guides the magnitude and phase of the blur image’s frequency coefficients to fit those of the ground truth by exploring the interdependencies of feature channels, fine-tunes the details of structures. The experimental results show that the proposed method outperformed the deblurring results compared to benchmark methods in terms of both qualitative evaluation and quantitative metrics.

FE-trans-net: Feature enhancement based single branch deep learning model for surface roughness detection

Real-time surface roughness measurement is crucial for modern manufacturing. Machine vision-based roughness measurement algorithms have the advantages of non-contact, high efficiency and adaptability. Light source is important for online machine vision-based roughness measurement. And different materials may need different light sources to extract more features. From the previous study, dual light sources are better than single light source for surface roughness prediction. However, it is inconvenient to assign two light sources for online detection equipment, and the two-branch model structure for dual light sources doubles the size of the model. To fully utilize the advantages of dual light sources, and avoid its disadvantages, a feature enhancement based single branch deep learning model FE-Trans-Net is proposed in this paper for surface roughness detection. Firstly, a dataset of different materials (Cu, Zn, Al, and Fe) shined with different light sources (white, red, green, red laser and green laser) is collected. Two most suitable light sources for different materials are chosen for dual light sources model as offline pre-training. In this model, lightweight cross-attention fusion (CAF-Trans) and graph convolutional channel attention (GCC-Atten) modules are designed to fuse the feature information of different light sources from the spatial and channel perspectives respectively, enabling the single-branch model to acquire the feature learning capability of different light sources. Then a single-branch network layer is remained as the online prediction. With the feature enhancement, it preserves the advantages of dual light source images, and has only half size of the dual light source model. Extensive experiments validate the effectiveness and generalization performance of the CAF-Trans and GCC-Atten modules, and the proposed FE-Trans-Net network achieves the best accuracy-efficiency tradeoff compared to other popular deep neural networks.