Tariq Mahmood^1,2, Tanzila Saba¹, Faten S. Alamri^3,*, Alishba Tahir⁴, Noor Ayesha⁵

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1173-1193, 2025, DOI:10.32604/cmc.2025.061150 - 26 March 2025

Abstract Innovation in learning algorithms has made retinal vessel segmentation and automatic grading techniques crucial for clinical diagnosis and prevention of diabetic retinopathy. The traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic retinopathy. While the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data, dual-modal diabetic retinopathy grading methods offer superior performance. However, the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to… More >

Hui Jin^1,2,*, Shuaiqi Xu¹, Chengyi Duan¹, Ruixue He¹, Ji Zhang¹

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1041-1055, 2025, DOI:10.32604/cmc.2025.060304 - 26 March 2025

Abstract Instance segmentation is crucial in various domains, such as autonomous driving and robotics. However, there is scope for improvement in the detection speed of instance-segmentation algorithms for edge devices. Therefore, it is essential to enhance detection speed while maintaining high accuracy. In this study, we propose you only look once-layer fusion (YOLO-LF), a lightweight instance segmentation method specifically designed to optimize the speed of instance segmentation for autonomous driving applications. Based on the You Only Look Once version 8 nano (YOLOv8n) framework, we introduce a lightweight convolutional module and design a lightweight layer aggregation module… More >

Xiaoyan Shao¹, Jiaqi Han^1,*, Lingling Li^1,*, Xuezhuan Zhao^1,2,3,4, Jingjing Yan¹

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 595-617, 2025, DOI:10.32604/cmc.2025.060295 - 26 March 2025

Abstract The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods. End-to-end model designs have gained significant attention for improving training efficiency. Most current algorithms rely on Convolutional Neural Networks (CNNs) for feature extraction. Although CNNs are proficient at capturing local features, they often struggle with global context, leading to incomplete and false Class Activation Mapping (CAM). To address these limitations, this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation (CPEWS) model, which improves feature extraction by utilizing the Vision Transformer… More >

Shijie Xiang, Dong Zhou, Dan Tian^*, Zihao Wang

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 497-515, 2025, DOI:10.32604/cmc.2025.060244 - 26 March 2025

Abstract Real-time semantic segmentation tasks place stringent demands on network inference speed, often requiring a reduction in network depth to decrease computational load. However, shallow networks tend to exhibit degradation in feature extraction completeness and inference accuracy. Therefore, balancing high performance with real-time requirements has become a critical issue in the study of real-time semantic segmentation. To address these challenges, this paper proposes a lightweight bilateral dual-residual network. By introducing a novel residual structure combined with feature extraction and fusion modules, the proposed network significantly enhances representational capacity while reducing computational costs. Specifically, an improved compound… More >

Can Wu^1,2, Wenyi Tang², Yunbo Rao^1,2,*, Yinjie Chen¹, Hui Ding², Shuzhen Zhu³, Yuanyuan Wang³

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1415-1434, 2025, DOI:10.32604/cmc.2025.059797 - 26 March 2025

Abstract Infrared unmanned aerial vehicle (UAV) target detection presents significant challenges due to the interplay between small targets and complex backgrounds. Traditional methods, while effective in controlled environments, often fail in scenarios involving long-range targets, high noise levels, or intricate backgrounds, highlighting the need for more robust approaches. To address these challenges, we propose a novel three-stage UAV segmentation framework that leverages uncertainty quantification to enhance target saliency. This framework incorporates a Bayesian convolutional neural network capable of generating both segmentation maps and probabilistic uncertainty maps. By utilizing uncertainty predictions, our method refines segmentation outcomes, achieving… More >

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 >

Jianuo Huang^1,2, Bohan Lai², Weiye Qiu³, Caixu Xu⁴, Jie He^1,5,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4841-4862, 2025, DOI:10.32604/cmc.2025.059733 - 06 March 2025

Abstract The self-attention mechanism of Transformers, which captures long-range contextual information, has demonstrated significant potential in image segmentation. However, their ability to learn local, contextual relationships between pixels requires further improvement. Previous methods face challenges in efficiently managing multi-scale features of different granularities from the encoder backbone, leaving room for improvement in their global representation and feature extraction capabilities. To address these challenges, we propose a novel Decoder with Multi-Head Feature Receptors (DMHFR), which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities: coarse, fine-grained, and full set.… More >

Jingjing Yan¹, Xuyang Zhuang^2,*, Xuezhuan Zhao^1,2, Xiaoyan Shao^1,*, Jiaqi Han¹

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5363-5386, 2025, DOI:10.32604/cmc.2025.059709 - 06 March 2025

Abstract The key to the success of few-shot semantic segmentation (FSS) depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set. Due to the few samples in the support set, FSS faces challenges such as intra-class differences, background (BG) mismatches between query and support sets, and ambiguous segmentation between the foreground (FG) and BG in the query set. To address these issues, The paper propose a multi-module network called CAMSNet, which includes four modules: the General Information Module (GIM), the Class Activation Map Aggregation (CAMA) module, the… More >

Xueli Shen, Meng Wang^*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4631-4647, 2025, DOI:10.32604/cmc.2025.059149 - 06 March 2025

Abstract In the field of Weakly Supervised Semantic Segmentation (WSSS), methods based on image-level annotation face challenges in accurately capturing objects of varying sizes, lacking sensitivity to image details, and having high computational costs. To address these issues, we improve the dual-branch architecture of the Conformer as the fundamental network for generating class activation graphs, proposing a multi-scale efficient weakly-supervised semantic segmentation method based on the improved Conformer. In the Convolution Neural Network (CNN) branch, a cross-scale feature integration convolution module is designed, incorporating multi-receptive field convolution layers to enhance the model’s ability to capture long-range… More >

Rifat Sarker Aoyon¹, Ismail Hossain², M. Abdullah-Al-Wadud³, Jia Uddin^4,*

CMES-Computer Modeling in Engineering & Sciences, Vol.142, No.3, pp. 2617-2640, 2025, DOI:10.32604/cmes.2025.060917 - 03 March 2025

Abstract This research introduces a unique approach to segmenting breast cancer images using a U-Net-based architecture. However, the computational demand for image processing is very high. Therefore, we have conducted this research to build a system that enables image segmentation training with low-power machines. To accomplish this, all data are divided into several segments, each being trained separately. In the case of prediction, the initial output is predicted from each trained model for an input, where the ultimate output is selected based on the pixel-wise majority voting of the expected outputs, which also ensures data privacy.… More >