Xuejing Li^*

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 1667-1681, 2025, DOI:10.32604/cmc.2025.062161 - 16 April 2025

Abstract Few-shot point cloud 3D object detection (FS3D) aims to identify and locate objects of novel classes within point clouds using knowledge acquired from annotated base classes and a minimal number of samples from the novel classes. Due to imbalanced training data, existing FS3D methods based on fully supervised learning can lead to overfitting toward base classes, which impairs the network’s ability to generalize knowledge learned from base classes to novel classes and also prevents the network from extracting distinctive foreground and background representations for novel class objects. To address these issues, this thesis proposes a… More >

Junzhe Zhang¹, Lei Tang^1,*, Xin Zhou²

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2643-2658, 2025, DOI:10.32604/cmc.2025.061690 - 16 April 2025

Abstract Fisheye cameras offer a significantly larger field of view compared to conventional cameras, making them valuable tools in the field of computer vision. However, their unique optical characteristics often lead to image distortions, which pose challenges for object detection tasks. To address this issue, we propose Yolo-CaSKA (Yolo with Contrastive Learning and Selective Kernel Attention), a novel training method that enhances object detection on fisheye camera images. The standard image and the corresponding distorted fisheye image pairs are used as positive samples, and the rest of the image pairs are used as negative samples, which More >

Yuanqing Li¹, Mengyao Dai¹, Sanfeng Zhang^1,2,*

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 309-333, 2025, DOI:10.32604/cmc.2025.060455 - 26 March 2025

Abstract Social media has significantly accelerated the rapid dissemination of information, but it also boosts propagation of fake news, posing serious challenges to public awareness and social stability. In real-world contexts, the volume of trustable information far exceeds that of rumors, resulting in a class imbalance that leads models to prioritize the majority class during training. This focus diminishes the model’s ability to recognize minority class samples. Furthermore, models may experience overfitting when encountering these minority samples, further compromising their generalization capabilities. Unlike node-level classification tasks, fake news detection in social networks operates on graph-level samples,… More >

Jian Feng^*, Yifan Guo, Cailing Du

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 5135-5151, 2025, DOI:10.32604/cmc.2025.059610 - 06 March 2025

Abstract Graph similarity learning aims to calculate the similarity between pairs of graphs. Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies, which can harm the semantic and structural information of graphs and overlook the rich structural information present in subgraphs. To address these issues, we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning. First, to tackle the problem of random augmentation disrupting the semantics and structure of the graph, we design a learnable augmentation method to selectively choose nodes and… 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 >

Jiyang Xu¹, Qi Wang^1,*, Xin Xiong², Weidong Min^1,3, Jiang Luo⁴, Di Gai¹, Qing Han^1,3

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 3921-3941, 2025, DOI:10.32604/cmc.2024.058586 - 06 March 2025

Abstract The unsupervised vehicle re-identification task aims at identifying specific vehicles in surveillance videos without utilizing annotation information. Due to the higher similarity in appearance between vehicles compared to pedestrians, pseudo-labels generated through clustering are ineffective in mitigating the impact of noise, and the feature distance between inter-class and intra-class has not been adequately improved. To address the aforementioned issues, we design a dual contrastive learning method based on knowledge distillation. During each iteration, we utilize a teacher model to randomly partition the entire dataset into two sub-domains based on clustering pseudo-label categories. By conducting contrastive… More >

Yujiao Tang¹, Yadong Wu^1,*, Yuanmei He², Jilin Liu¹, Weihan Zhang¹

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2331-2352, 2025, DOI:10.32604/cmc.2024.059115 - 17 February 2025

Abstract Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion… More >

Hengyang Liu¹, Yang Yuan^1,*, Pengcheng Ren¹, Chengyun Song¹, Fen Luo²

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 543-560, 2025, DOI:10.32604/cmc.2024.056478 - 03 January 2025

Abstract Existing semi-supervised medical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch. However, current copy-paste methods have three limitations: (1) training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information; (2) low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data; (3) the segmentation performance in low-contrast and local regions is less than optimal. We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy (SADT), which enhances feature diversity and learns high-quality features to overcome these problems. To be more… More >

Jian Feng^*, Tian Liu, Cailing Du

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2895-2909, 2024, DOI:10.32604/cmc.2024.056434 - 18 November 2024

Abstract Unsupervised learning methods such as graph contrastive learning have been used for dynamic graph representation learning to eliminate the dependence of labels. However, existing studies neglect positional information when learning discrete snapshots, resulting in insufficient network topology learning. At the same time, due to the lack of appropriate data augmentation methods, it is difficult to capture the evolving patterns of the network effectively. To address the above problems, a position-aware and subgraph enhanced dynamic graph contrastive learning method is proposed for discrete-time dynamic graphs. Firstly, the global snapshot is built based on the historical snapshots… More >

Jieren Cheng^1,3, Jimei Li^1,3,*, Faqiang Zeng^1,3, Zhicong Tao^1,3, Yue Yang^2,3

CMC-Computers, Materials & Continua, Vol.80, No.1, pp. 281-298, 2024, DOI:10.32604/cmc.2024.051816 - 18 July 2024

Abstract Contrastive learning is a significant research direction in the field of deep learning. However, existing data augmentation methods often lead to issues such as semantic drift in generated views while the complexity of model pre-training limits further improvement in the performance of existing methods. To address these challenges, we propose the Efficient Clustering Network based on Matrix Factorization (ECN-MF). Specifically, we design a batched low-rank Singular Value Decomposition (SVD) algorithm for data augmentation to eliminate redundant information and uncover major patterns of variation and key information in the data. Additionally, we design a Mutual Information-Enhanced More >