Woongkyu Park¹, Yeongyu Choi², Mahammad Shareef Mekala³, Gyu Sang Choi¹, Kook-Yeol Yoo¹, Ho-youl Jung^1,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 3965-3981, 2025, DOI:10.32604/cmc.2025.059966 - 06 March 2025

Abstract Designing fast and accurate neural networks is becoming essential in various vision tasks. Recently, the use of attention mechanisms has increased, aimed at enhancing the vision task performance by selectively focusing on relevant parts of the input. In this paper, we concentrate on squeeze-and-excitation (SE)-based channel attention, considering the trade-off between latency and accuracy. We propose a variation of the SE module, called squeeze-and-excitation with layer normalization (SELN), in which layer normalization (LN) replaces the sigmoid activation function. This approach reduces the vanishing gradient problem while enhancing feature diversity and discriminability of channel attention. In… More >

Yi Zuo, Zhenping Chen^*, Jing Feng, Yunhao Fan

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4649-4667, 2025, DOI:10.32604/cmc.2025.059472 - 06 March 2025

Abstract Image classification is crucial for various applications, including digital construction, smart manufacturing, and medical imaging. Focusing on the inadequate model generalization and data privacy concerns in few-shot image classification, in this paper, we propose a federated learning approach that incorporates privacy-preserving techniques. First, we utilize contrastive learning to train on local few-shot image data and apply various data augmentation methods to expand the sample size, thereby enhancing the model’s generalization capabilities in few-shot contexts. Second, we introduce local differential privacy techniques and weight pruning methods to safeguard model parameters, perturbing the transmitted parameters to ensure More >

Naikang Zhong¹, Xiao Lin^1,2,3,4,*, Wen Du⁵, Jin Shi⁶

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5285-5306, 2025, DOI:10.32604/cmc.2025.059102 - 06 March 2025

Abstract Multi-label image classification is a challenging task due to the diverse sizes and complex backgrounds of objects in images. Obtaining class-specific precise representations at different scales is a key aspect of feature representation. However, existing methods often rely on the single-scale deep feature, neglecting shallow and deeper layer features, which poses challenges when predicting objects of varying scales within the same image. Although some studies have explored multi-scale features, they rarely address the flow of information between scales or efficiently obtain class-specific precise representations for features at different scales. To address these issues, we propose… More >

Kun Liu¹, Chen Bao^1,*, Sidong Liu²

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4451-4468, 2025, DOI:10.32604/cmc.2024.059053 - 06 March 2025

Abstract Large amounts of labeled data are usually needed for training deep neural networks in medical image studies, particularly in medical image classification. However, in the field of semi-supervised medical image analysis, labeled data is very scarce due to patient privacy concerns. For researchers, obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding. In addition, skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions. In this paper, we propose a model called Coalition Sample Relation Consistency (CSRC),… More >

Tanzila Saba¹, Muhammad Mujahid¹, Shaha Al-Otaibi², Noor Ayesha³, Amjad Rehman Khan^1,*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3337-3353, 2025, DOI:10.32604/cmc.2025.060163 - 17 February 2025

Abstract Osteosarcomas are malignant neoplasms derived from undifferentiated osteogenic mesenchymal cells. It causes severe and permanent damage to human tissue and has a high mortality rate. The condition has the capacity to occur in any bone; however, it often impacts long bones like the arms and legs. Prompt identification and prompt intervention are essential for augmenting patient longevity. However, the intricate composition and erratic placement of osteosarcoma provide difficulties for clinicians in accurately determining the scope of the afflicted area. There is a pressing requirement for developing an algorithm that can automatically detect bone tumors with… More >

Jahida Subhedar^1,2, Anurag Mahajan^1,*, Shabana Urooj³, Neeraj Kumar Shukla^4,5

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2831-2847, 2025, DOI:10.32604/cmc.2025.059350 - 17 February 2025

Abstract Retinal Optical Coherence Tomography (OCT) images, a non-invasive imaging technique, have become a standard retinal disease detection tool. Due to disease, there are morphological and textural changes in the layers of the retina. Classifying OCT images is challenging, as the morphological manifestations of different diseases may be similar. The OCT images capture the reflectivity characteristics of the retinal tissues. Retinal diseases change the reflectivity property of retinal tissues, resulting in texture variations in OCT images. We propose a hybrid approach to OCT image classification in which the Convolution Neural Network (CNN) model is trained using… More >

Yaoxuan Zhu, Hua Yang, Bin Zhu^*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 1947-1968, 2025, DOI:10.32604/cmc.2024.057866 - 17 February 2025

Abstract The emergence of adversarial examples has revealed the inadequacies in the robustness of image classification models based on Convolutional Neural Networks (CNNs). Particularly in recent years, the discovery of natural adversarial examples has posed significant challenges, as traditional defense methods against adversarial attacks have proven to be largely ineffective against these natural adversarial examples. This paper explores defenses against these natural adversarial examples from three perspectives: adversarial examples, model architecture, and dataset. First, it employs Class Activation Mapping (CAM) to visualize how models classify natural adversarial examples, identifying several typical attack patterns. Next, various common… More >

Syed Tasnimul Karim Ayon^1,#, Farhan Md. Siraj^1,#, Jia Uddin^2,*

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 499-520, 2025, DOI:10.32604/cmc.2025.058361 - 03 January 2025

Abstract This study investigates the application of Learnable Memory Vision Transformers (LMViT) for detecting metal surface flaws, comparing their performance with traditional CNNs, specifically ResNet18 and ResNet50, as well as other transformer-based models including Token to Token ViT, ViT without memory, and Parallel ViT. Leveraging a widely-used steel surface defect dataset, the research applies data augmentation and t-distributed stochastic neighbor embedding (t-SNE) to enhance feature extraction and understanding. These techniques mitigated overfitting, stabilized training, and improved generalization capabilities. The LMViT model achieved a test accuracy of 97.22%, significantly outperforming ResNet18 (88.89%) and ResNet50 (88.90%), as well… More >

Mohd Anjum¹, Naoufel Kraiem², Hong Min^3,*, Ashit Kumar Dutta⁴, Yousef Ibrahim Daradkeh⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.1, pp. 357-384, 2025, DOI:10.32604/cmes.2024.057889 - 17 December 2024

Abstract Machine learning (ML) is increasingly applied for medical image processing with appropriate learning paradigms. These applications include analyzing images of various organs, such as the brain, lung, eye, etc., to identify specific flaws/diseases for diagnosis. The primary concern of ML applications is the precise selection of flexible image features for pattern detection and region classification. Most of the extracted image features are irrelevant and lead to an increase in computation time. Therefore, this article uses an analytical learning paradigm to design a Congruent Feature Selection Method to select the most relevant image features. This process… More >

Muhammad Ahmad^1,*, Manuel Mazzara², Salvatore Distefano³, Adil Mehmood Khan⁴, Hamad Ahmed Altuwaijri⁵

CMC-Computers, Materials & Continua, Vol.81, No.1, pp. 503-532, 2024, DOI:10.32604/cmc.2024.056318 - 15 October 2024

Abstract Disjoint sampling is critical for rigorous and unbiased evaluation of state-of-the-art (SOTA) models e.g., Attention Graph and Vision Transformer. When training, validation, and test sets overlap or share data, it introduces a bias that inflates performance metrics and prevents accurate assessment of a model’s true ability to generalize to new examples. This paper presents an innovative disjoint sampling approach for training SOTA models for the Hyperspectral Image Classification (HSIC). By separating training, validation, and test data without overlap, the proposed method facilitates a fairer evaluation of how well a model can classify pixels it was… More >