Residual Channel Attention Research Articles

Residual channel attention based sample adaptation few-shot learning for hyperspectral image classification.

Few-shot learning (FSL) uses prior knowledge and supervised experience to effectively classify hyperspectral images (HSIs), thereby reducing the cost of large numbers of labeled samples. However, existing few-shot methods ignore the correlation between cross-domain feature channels, and the feature representation ability is insufficient. To address above issue, this paper proposes a novel Residual Channel Attention Based Sample Adaptation Few-Shot Learning for Hyperspectral Image Classification(RCASA-FSL) for hyperspectral image classification (HSIC), which can capture and enhance cross-domain dependencies through multi-layer residual connection and random-based feature recalibration. Specifically, a Deep Residual Feature Channel Attention Mechanism (DRFCAM) is designed to obtain cross-domain dependencies by residual concatenation, and further the residual structure is stacked for mining depth discrimination information. Furthermore, a new Random-based Feature Recalibration Module (RFRM) is proposed to reassign the feature weights via random matrix, which fully explore feature weight relationships to guide the sample adaptation process. Besides, we design a joint loss function with combining the FSL loss and domain adaptive loss for further optimization model. Experiments conducted on several standard hyperspectral datasets demonstrate that the proposed RCASA-FSL is superior to other FSL techniques in both quantitative and qualitative aspects.

A novel intelligent fault diagnosis method for gearbox based on multi-dimensional attention denoising convolution.

In the field of intelligent fault diagnosis, particularly concerning rotating machinery, convolutional neural networks (CNNs) face significant challenges when applied to real industrial vibration data. These data are not only contaminated by various types of noise but also exhibit fault features that vary across different scales. Consequently, the effective suppression of extraneous noise and accurate extraction of multi-scale fault features are crucial issues. To address these challenges, this study proposes a novel deep neural network framework, termed the Multidimensional Fusion Residual Attention Network (MFRANet), for gearbox fault diagnosis. The MFRANet employs a multi-scale deep separable convolution module to thoroughly investigate the fundamental characteristics of the original vibration signals in both the time and time-frequency domains. To enhance the detailed analysis of diagnostic data and mitigate the risks of overfitting and noise interference, an efficient residual channel attention module is incorporated to weight and denoise the feature maps. Additionally, an external attention module is introduced to create implicit connections between the denoised multi-scale feature maps and to highlight potential correlations within the sample data, thereby improving the accuracy of fault diagnosis. Experimental evaluations on a gearbox fault dataset demonstrate that the proposed method surpasses several benchmark and state-of-the-art techniques in terms of diagnostic performance, exhibiting robust noise resilience across various noise levels. This indicates enhanced reliability and accuracy in gearbox fault diagnosis, providing an innovative and efficient solution for fault diagnosis in rotating machinery. The study underscores the contributions of artificial intelligence through the innovative structure of the method and the integration of advanced deep learning modules, while its engineering application is evidenced by addressing practical challenges in rotating machinery fault diagnosis. This work meets the urgent need for reliable diagnostic methods in industrial environments.

Research on fault diagnosis of mechanical component in high-speed train based on one-dimensional convolutional block residual channel attention

The yaw damper and the rolling bearing are key components to ensure the safe and reliable operation of high-speed trains. However, fault identification in these components remains challenging, with traditional feature extraction methods often suffering from low diagnostic accuracy. To address these issues, a one-dimensional convolutional block residual channel attention (1DCBRCA) method for fault diagnosis of high-speed train components is introduced. Firstly, the convolutional layer is constructed for feature extraction, and the convolution block attention module is utilized for adaptive feature optimization in both channel and space dimensions. Subsequently, a residual neural network model is established, with channel attention added after each residual block to focus on critical feature information, which is used for adjusting the weight parameters. Furthermore, the proposed method was validated through damper fault experiments and bearing fault experiments. Comparative analysis with state-of-the-art methods demonstrated that the proposed 1DCBRCA approach achieves higher diagnostic accuracy, confirming its potential to enhance fault diagnosis in high-speed train components.

Super-resolution reconstruction improves multishell diffusion: using radiomics to predict adult-type diffuse glioma IDH and grade.

Multishell diffusion scanning is limited by low spatial resolution. We sought to improve the resolution of multishell diffusion images through deep learning-based super-resolution reconstruction (SR) and subsequently develop and validate a prediction model for adult-type diffuse glioma, isocitrate dehydrogenase status and grade 2/3 tumors. A simple diffusion model (DTI) and three advanced diffusion models (DKI, MAP, and NODDI) were constructed based on multishell diffusion scanning. Migration was performed with a generative adversarial network based on deep residual channel attention networks, after which images with 2x and 4x resolution improvements were generated. Radiomic features were used as inputs, and diagnostic models were subsequently constructed via multiple pipelines. This prospective study included 90 instances (median age, 54.5 years; 39 men) diagnosed with adult-type diffuse glioma. Images with both 2x- and 4x-improved resolution were visually superior to the original images, and the 2x-improved images allowed better predictions than did the 4x-improved images (P<.001). A comparison of the areas under the curve among the multiple pipeline-constructed models revealed that the advanced diffusion models did not have greater diagnostic performance than the simple diffusion model (P>.05). The NODDI model constructed with 2x-improved images had the best performance in predicting isocitrate dehydrogenase status (AUC_validation=0.877; Brier score=0.132). The MAP model constructed with the original images performed best in classifying grade 2 and grade 3 tumors (AUC_validation=0.806; Brier score=0.168). SR improves the resolution of multishell diffusion images and has different advantages in achieving different goals and creating different target diffusion models.

BMAD-Net: An attention mechanism network using block match for laboratory X-ray Microscopy denoising

CNNs have been widely used for image denoising. An attention mechanism network using block match for laboratory X-ray Microscopy denoising is proposed. The similar block is introduced into a CNN model to capture the global information connections of the images, which complements the information loss by weakening long-distance dependencies with increased convolution network depth. A multi-scale convolutional subnetwork is designed to enhance the receptive field as the noise feature extraction module. Then, by reassigning weights to the feature channels, a residual channel attention block is designed to improve the feature channel’s availability. Both experiments on bronze coins and fossils show that the proposed method can perform effective image denoising within 0.1s exposure time, and the image quality is comparable with those within 3s exposure time, reducing the existing acquisition time.

ETCNN: An ensemble transformer-convolutional neural network for automatic analysis of fetal heart rate

ObjectiveTraditional methods face challenges in accurately analyzing fetal heart rate (FHR) signals due to the complexity of accelerations and decelerations (Acc/Dec) and their cyclic definition relationship with baseline. We aim to develop a deep learning model, Ensemble Transformer-Convolutional Neural Network (ETCNN), to improve baseline/Acc/Dec determination accuracy and validate its generalization across multi-center and multi-device test datasets. MethodsWe proposed ETCNN as a solution, treating FHR analysis as a one-dimensional signal segmentation problem. ETCNN consists of four subnetworks (TCNNs), each equipped with convolutional kernel size of 21, 31, 61, and 81, respectively. Each subnetwork integrates Channel-Residual (C-Res) modules and Channel Cross fusion with Transformer (CCT) modules. C-Res modules dynamically prune irrelevant channels, focusing on critical FHR episodes, while CCT modules harness multi-scale features to narrow semantic gaps. ResultsTrained on Lille Catholic University’s open-access database (LCU-DB), ETCNN’s performance surpassed twelve traditional methods and three deep learning models across four independent multi-center and multi-device test datasets. Ablation experiments demonstrated the effectiveness of ensemble learning, multi-scale convolution, residual channel attention, channel cross fusion attention, and multi-head attention in improving performance. Conclusion and significanceETCNN shows promise for accurate and efficient FHR analysis, with successful generalization across various datasets. Its advancements hold potential for clinical applications in fetal monitoring.

ReLAP-Net: Residual Learning and Attention Based Parallel Network for Hyperspectral and Multispectral Image Fusion

Remote sensing applications require high-resolution images to obtain precise information about the Earth???s surface. Multispectral images have high spatial resolution but low spectral resolution. Hyperspectral images have high spectral resolution but low spatial resolution. This study proposes a residual learning and attention-based parallel network based on residual network and channel attention. The network performs image fusion of a high spatial resolution multispectral image and a low spatial resolution hyperspectral image. The network training and fusion experiments are conducted on four public benchmark data sets to show the effectiveness of the proposed model. The fusion performance is compared with classical signal processing???based image fusion techniques. Four image metrics are used for the quantitative evaluation of the fused images. The proposed network improved fusion ability by reducing the root mean square error and relative dimensionless global error in synthesis and increased the peak signal-to-noise ratio when compared to other state-of-the-art models.

Swin Transformer Based Network with Residual Channel Attention for Bit-Depth Expansion

Swin Transformer Based Network with Residual Channel Attention for Bit-Depth Expansion

Skin lesion classification with multi-level fusion of Swin-T and ConvNeXt

Skin cancer is a significant public health issue, and computer-aided diagnosis technology can effectively alleviate this burden. Accurate identification of skin lesion types is crucial when employing computer-aided diagnosis. This study proposes a multi-level attention cascaded fusion model based on Swin-T and ConvNeXt. It employed hierarchical Swin-T and ConvNeXt to extract global and local features, respectively, and introduced residual channel attention and spatial attention modules for further feature extraction. Multi-level attention mechanisms were utilized to process multi-scale global and local features. To address the problem of shallow features being lost due to their distance from the classifier, a hierarchical inverted residual fusion module was proposed to dynamically adjust the extracted feature information. Balanced sampling strategies and focal loss were employed to tackle the issue of imbalanced categories of skin lesions. Experimental testing on the ISIC2018 and ISIC2019 datasets yielded accuracy, precision, recall, and F1-Score of 96.01%, 93.67%, 92.65%, and 93.11%, respectively, and 92.79%, 91.52%, 88.90%, and 90.15%, respectively. Compared to Swin-T, the proposed method achieved an accuracy improvement of 3.60% and 1.66%, and compared to ConvNeXt, it achieved an accuracy improvement of 2.87% and 3.45%. The experiments demonstrate that the proposed method accurately classifies skin lesion images, providing a new solution for skin cancer diagnosis.

Deep RegNet-150 architecture for single image super resolution of real-time unpaired image data

Single Image Super-Resolution (SISR) is a fundamental computer vision task aimed at enhancing the spatial resolution and quality of low-resolution images. In recent years, deep learning techniques have revolutionized the field of SISR, enabling remarkable advancements in image enhancement. Typically, the Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) based deep learning techniques are employed for the SISR. However, the existing CNN and GAN architectures lag in providing maximum performance in terms of SSIM and PSNR. In this paper, a regression deep learning architecture is designed for the SISR. The proposed Deep Regression Network with 150 (Deep RegNet-150) is designed as a U-net. The proposed Deep RegNet-150 includes up-sampling and down-sampling portions with Residual Channel Attention Block (RCAB) for SISR. The RCAB acts as the building block of image super resolution (SR) by including ReLU and Conv layer. The performance of the proposed technique is evaluated on different image datasets, including a text image dataset and an unpaired dataset. The performance in terms of SSIM and PSNR for 4X and 8X SR is evaluated. The proposed Deep RegNet-150 attained maximum PSNR / SSIM values of 43.99 / 0.989 and 42.73 / 0.987 for 4X and 8X SR of the benchmark dataset, respectively. The 4X and 8X SR of unpaired datasets attained 46.13 / 0.991 and 45.97 / 0.990 of PSNR /SSIM, respectively. Ultimately, it proves that the Deep RegNet-150 is an effective deep learning architecture for the SISR.

Enhancing Chest X-ray Image Super-Resolution through Residual Group and Channel Attention

Enhancing Chest X-ray Image Super-Resolution through Residual Group and Channel Attention

Densely integrated multi-branch attentive net for image dehazing

Single image dehazing is a fundamental but challenging task in image processing. Various deep learning-based methods have achieved great dehazing performance. However, there are still hazy residues, even color distortion and texture loss when removing haze from complex outdoor images in dense hazy scenes. A densely integrated multi-branch attentive net for image dehazing is proposed in the paper to address the above problems. The network includes a multi-scale feature extraction module and a dense-feature fusion module. The multi-scale feature extraction module adopts a multi-branch structure composed of residual channel attention blocks, which can expand the receptive field and filter the extracted features of diverse scales by weighting for fusion. It raises network learning accuracy. The dense-feature fusion module contains a multi-level feature fusion module for front and back layers, a color information renovation module, and a feature enhancement module. It achieves dynamically adjusting the channel weights of features at diverse scales, learning rich context information and suppressing redundant information, and compensating for the lack of color and texture information. The dense-feature fusion module bolsters the generalization capability of the network. The proposed method achieves superior objective and subjective evaluation results via quantitative and qualitative experiments on synthetic hazy images and natural hazy images, with better generalization ability and dehazing effect than the current SOTA dehazing algorithms, and effectively ameliorates the color distortion and incomplete dehazing.

Light field angular super resolution based on residual channel attention and classification up-sampling

Light field angular super resolution based on residual channel attention and classification up-sampling

A hybrid convolution transformer for hyperspectral image classification

ABSTRACT Hyperspectral images play a crucial role in remote sensing applications surveillance, environment and precision agriculture, containing abundant object information. However, they often face challenges such as limited labelled data and imbalanced classes. In recent years, convolutional neural networks (CNNs) have shown impressive performance in computer vision tasks, including hyperspectral image classification. The emergence of transformers has also attracted attention for hyperspectral image analysis due to their promising capabilities. Nevertheless, transformers typically demand a substantial amount of training data, making their application challenging in scenarios with limited labelled samples. To overcome this limitation, we propose a hybrid convolution transformer framework. Our method uses a vision transformer and a residual 3D convolutional neural network model. It also uses a sequence aggregation layer to avoid overfitting issues that come up when there isn’t enough training data. Our proposed residual channel attention module captures richer spatial-spectral complementary information and maintains spectral details during the feature extraction process. We conducted experiments on three benchmark datasets. The proposed model achieved state of the art performance 99.75 % , 99.46 % and 99.95 % in terms of overall accuracy (OA) using only 5 % , 5 % and 10 % labelled training samples respectively. Which is better than other state of the art methods.

Multi-path residual attention network for cancer diagnosis robust to a small number of training data of microscopic hyperspectral pathological images

Duct cancer is a malignant disease with higher mortality rates in males than in females, emphasizing the need for early diagnosis to improve treatment outcomes. Although various imaging modalities such as magnetic resonance imaging (MRI) and computed tomography scan (CT-scan) have been used for pathological analysis, hyperspectral imaging stands out as a promising approach, especially when combined with deep learning techniques. Hyperspectral imaging provides detailed information on tissue composition and biochemical properties, enabling better distinction between cancerous and healthy tissues. Although previous research based on hyperspectral imaging shows high accuracy, no previous research has used a small amount of training data, despite this being the usual case in medical image applications. Therefore, we propose a multi-path residual attention network (MRA-Net) with chunked residual channel attention (CRCA), which is a novel deep learning model specifically designed to address the challenges posed by limited training data, with a particular focus on using hyperspectral images. By leveraging the unique spectral information provided by hyperspectral imaging, MRA-Net extracts distinctive features, enhancing its ability to differentiate between cancerous and healthy tissues.We conducted the training and validation of our model using a publicly accessible dataset, resulting in an accuracy of 84.31% and a weighted harmonic mean of precision and recall (F1 score) of 84.29%, demonstrating its state-of-the-art performance compared to existing methods.

XVDPU: A High-Performance CNN Accelerator on the Versal Platform Powered by the AI Engine

Today, convolutional neural networks (CNNs) are widely used in computer vision applications. However, the trends of higher accuracy and higher resolution generate larger networks. The requirements of computation or I/O are the key bottlenecks. In this article, we propose XVDPU: the AI Engine (AIE)-based CNN accelerator on Versal chips to meet heavy computation requirements. To resolve the IO bottleneck, we adopt several techniques to improve data reuse and reduce I/O requirements. An arithmetic logic unit is further proposed that can better balance resource utilization, new feature support, and efficiency of the whole system. We have successfully deployed more than 100 CNN models with our accelerator. Our experimental results show that the 96-AIE-core implementation can achieve 1,653 frames per second (FPS) for ResNet50 on VCK190, which is 9.8× faster than the design on ZCU102 running at 168.5 FPS. The 256-AIE-core implementation can further achieve 4,050 FPS. We propose a tilling strategy to achieve feature-map-stationary for high-definition CNN with the accelerator, achieving 3.8× FPS improvement on the residual channel attention network and 3.1× on super-efficient super-resolution. This accelerator can also solve the 3D convolution task in disparity estimation, achieving end-to-end performance of 10.1 FPS with all the optimizations.

Enhancing medical text detection with vision-language pre-training and efficient segmentation

AbstractDetecting text within medical images presents a formidable challenge in the domain of computer vision due to the intricate nature of textual backgrounds, the dense text concentration, and the possible existence of extreme aspect ratios. This paper introduces an effective and precise text detection system tailored to address these challenges. The system incorporates an optimized segmentation module, a trainable post-processing method, and leverages a vision-language pre-training model (oCLIP). Specifically, our segmentation head integrates three essential components: the Feature Pyramid Network (FPN) module, which combines a residual structure and channel attention mechanism; the Efficient Feature Enhancement Module (EFEM); and the Multi-Scale Feature Fusion with RSEConv (MSFM-RSE), designed specifically for multi-scale feature fusion based on RSEConv. By introducing a residual structure and channel attention mechanism into the FPN module, the convolutional layers are replaced with RSEConv layers that employ a channel attention mechanism, further augmenting the representational capacity of the feature maps. The EFEM, designed as a cascaded U-shaped module, incorporates a spatial attention mechanism to introduce multi-level information, thereby enhancing segmentation performance. Subsequently, the MSFM-RSE adeptly amalgamates features from various depths and scales of the EFEM to generate comprehensive final features tailored for segmentation purposes. Additionally, a post-processing module employs a differentiable binarization strategy, allowing the segmentation network to dynamically determine the binarization threshold. Building on the system’s improvement, we introduce a vision-language pre-training model that undergoes extensive training on various visual language understanding tasks. This pre-trained model acquires detailed visual and semantic representations, further reinforcing both the accuracy and robustness in text detection when integrated with the segmentation module. The performance of our proposed model was evaluated through experiments on medical text image datasets, demonstrating excellent results. Multiple benchmark experiments validate its superior performance in comparison to existing methods. Code is available at: https://github.com/csworkcode/VLDBNet.

Light field image coding using a residual channel attention network–based view synthesis

PurposeLight field images (LFIs) have gained popularity as a technology to increase the field of view (FoV) of plenoptic cameras since they can capture information about light rays with a large FoV. Wide FoV causes light field (LF) data to increase rapidly, which restricts the use of LF imaging in image processing, visual analysis and user interface. Effective LFI coding methods become of paramount importance. This paper aims to eliminate more redundancy by exploring sparsity and correlation in the angular domain of LFIs, as well as mitigate the loss of perceptual quality of LFIs caused by encoding.Design/methodology/approachThis work proposes a new efficient LF coding framework. On the coding side, a new sampling scheme and a hierarchical prediction structure are used to eliminate redundancy in the LFI's angular and spatial domains. At the decoding side, high-quality dense LF is reconstructed using a view synthesis method based on the residual channel attention network (RCAN).FindingsIn three different LF datasets, our proposed coding framework not only reduces the transmitted bit rate but also maintains a higher view quality than the current more advanced methods.Originality/value(1) A new sampling scheme is designed to synthesize high-quality LFIs while better ensuring LF angular domain sparsity. (2) To further eliminate redundancy in the spatial domain, new ranking schemes and hierarchical prediction structures are designed. (3) A synthetic network based on RCAN and a novel loss function is designed to mitigate the perceptual quality loss due to the coding process.

ERCP-Net: a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network

Plant leaf diseases are a major cause of plant mortality, especially in crops. Timely and accurately identifying disease types and implementing proper treatment measures in the early stages of leaf diseases are crucial for healthy plant growth. Traditional plant disease identification methods rely heavily on visual inspection by experts in plant pathology, which is time-consuming and requires a high level of expertise. So, this approach fails to gain widespread adoption. To overcome these challenges, we propose a channel extension residual structure and adaptive channel attention mechanism for plant leaf disease classification network (ERCP-Net). It consists of channel extension residual block (CER-Block), adaptive channel attention block (ACA-Block), and bidirectional information fusion block (BIF-Block). Meanwhile, an application for the real-time detection of plant leaf diseases is being created to assist precision agriculture in practical situations. Finally, experiments were conducted to compare our model with other state-of-the-art deep learning methods on the PlantVillage and AI Challenger 2018 datasets. Experimental results show that our model achieved an accuracy of 99.82% and 86.21%, respectively. Also, it demonstrates excellent robustness and scalability, highlighting its potential for practical implementation.

Multiscale Cross-Connected Dehazing Network With Scene Depth Fusion.

In this article, we propose a multiscale cross-connected dehazing network with scene depth fusion. We focus on the correlation between a hazy image and the corresponding depth image. The model encodes and decodes the hazy image and the depth image separately and includes cross connections at the decoding end to directly generate a clean image in an end-to-end manner. Specifically, we first construct an input pyramid to obtain the receptive fields of the depth image and the hazy image at multiple levels. Then, we add the features of the corresponding dimensions in the input pyramid to the encoder. Finally, the two paths of the decoder are cross-connected. In addition, the proposed model uses wavelet pooling and residual channel attention modules (RCAMs) as components. A series of ablation experiments shows that the wavelet pooling and RCAMs effectively improve the performance of the model. We conducted extensive experiments on multiple dehazing datasets, and the results show that the model is superior to other advanced methods in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and subjective visual effects. The source code and supplementary are available at https://github.com/CCECfgd/MSCDN-master.