Spatial Channel Attention for Deep Convolutional Neural Networks

Liu, Tonglai; Luo, Ronghai; Xu, Longqin; Feng, Dachun; Cao, Liang; Liu, Shuangyin; Guo, Jianjun

doi:10.3390/math10101750

Cited by 39 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of the proposed MS-DAM, we compared and analyzed the classification results of the model with those of existing self-attention methods. The six existing self-attention methods include SENet, bottleneck attention module (BAM) 36 , CBAM, efficient channel attention for deep convolutional neural networks (ECA-Net) 37 , attention gated networks (AGUNet) 38 , and MS-CAM. Our method, MS-DAM, can be used as an independent modules module alongside these methods.…”

Section: Resultsmentioning

confidence: 99%

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

Moon,

Lee,

Baek

et al. 2023

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

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

Moon,

Lee,

Baek

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The primary function of spatial attention is to capture the interdependencies between different regions of an image by emphasizing the important regions and suppressing the less relevant ones. This is achieved through the use of a gating mechanism that generates a spatial map, which is multiplied by the input features to amplify or attenuate them [ 43 ]. This gating mechanism is typically implemented using a learnable parameter that is trained alongside the rest of the model.…”

Section: Methodsmentioning

confidence: 99%

Spatial-attention ConvMixer architecture for classification and detection of gastrointestinal diseases using the Kvasir dataset

Demirbaş,

Üzen,

Fırat

2024

Health Inf Sci Syst

View full text Add to dashboard Cite

Gastrointestinal (GI) disorders, encompassing conditions like cancer and Crohn’s disease, pose a significant threat to public health. Endoscopic examinations have become crucial for diagnosing and treating these disorders efficiently. However, the subjective nature of manual evaluations by gastroenterologists can lead to potential errors in disease classification. In addition, the difficulty of diagnosing diseased tissues in GI and the high similarity between classes made the subject a difficult area. Automated classification systems that use artificial intelligence to solve these problems have gained traction. Automatic detection of diseases in medical images greatly benefits in the diagnosis of diseases and reduces the time of disease detection. In this study, we suggested a new architecture to enable research on computer-assisted diagnosis and automated disease detection in GI diseases. This architecture, called Spatial-Attention ConvMixer (SAC), further developed the patch extraction technique used as the basis of the ConvMixer architecture with a spatial attention mechanism (SAM). The SAM enables the network to concentrate selectively on the most informative areas, assigning importance to each spatial location within the feature maps. We employ the Kvasir dataset to assess the accuracy of classifying GI illnesses using the SAC architecture. We compare our architecture’s results with Vanilla ViT, Swin Transformer, ConvMixer, MLPMixer, ResNet50, and SqueezeNet models. Our SAC method gets 93.37% accuracy, while the other architectures get respectively 79.52%, 74.52%, 92.48%, 63.04%, 87.44%, and 85.59%. The proposed spatial attention block improves the accuracy of the ConvMixer architecture on the Kvasir, outperforming the state-of-the-art methods with an accuracy rate of 93.37%.

show abstract

“…In the case of violence detection, useful information is the nature of interaction dynamics between people that we want to classify and localize in an image. Hereby, the Convolutional Block Attention Module (CBAM) is proposed in [22] and its concept used in [25][26][27]; that consist of two main sub-modules (as shown in Figure 1): 1) Channel attention module, and 2) Spatial attention module. As illustrated in Figure 1, the input features input to the channel attention, in shape of F ∈ C×H×W.…”

Section: Convolutional Block Attention Modulementioning

confidence: 99%

Violence Detection Enhancement by Involving Convolutional Block Attention Modules Into Various Deep Learning Architectures: Comprehensive Case Study for UBI-Fights Dataset

Abbass

Kang

2023

IEEE Access

View full text Add to dashboard Cite

The violence detection in surveillance videos is a complicated task, due to the requirements of extracting the spatio-temporal features in different videos environment, and various videos prospective cases. Hereby, in this paper, different architectures are proposed to perform this task in high performance, by using the UBI-Fights dataset as a comprehensive case study. The proposed architectures are based on involving the Convolutional Block Attention Modules (CBAM) with other simple layers (e.g., ConvLSTM2D or Conv2D&LSTM). In addition, using the Categorical Focal Loss (CFL) as loss function during architectures training to increase the focus on the most important features. To evaluate the proposed architectures, the performance metrics like are Area Under the Curve (AUC), and Equal Error Rate (EER); are mainly used, to declare the architecture ability of identifying the violence correctly, with low interaction value between classes. The performance results declare the ability of the proposed architectures, to achieve higher results that the state of art techniques. For example, the Conv2D&LSTM based architecture, get AUC value of 0.9493, and EER value of 0.0507; that outperform the most of the other proposed ones, and the state of art performance.

show abstract

Spatial Channel Attention for Deep Convolutional Neural Networks

Cited by 39 publications

References 16 publications

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

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

Spatial-attention ConvMixer architecture for classification and detection of gastrointestinal diseases using the Kvasir dataset

Violence Detection Enhancement by Involving Convolutional Block Attention Modules Into Various Deep Learning Architectures: Comprehensive Case Study for UBI-Fights Dataset

Contact Info

Product

Resources

About