Tao Yi^1,3, Xingshu Chen^1,2,*, Mingdong Yang³, Qindong Li¹, Yi Zhu¹

CMES-Computer Modeling in Engineering & Sciences, Vol.140, No.1, pp. 929-955, 2024, DOI:10.32604/cmes.2024.048793

Abstract Due to the rapid evolution of Advanced Persistent Threats (APTs) attacks, the emergence of new and rare attack samples, and even those never seen before, make it challenging for traditional rule-based detection methods to extract universal rules for effective detection. With the progress in techniques such as transfer learning and meta-learning, few-shot network attack detection has progressed. However, challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning, difficulties in capturing rich information from original flow in the case of insufficient samples, and the… More >

Shoukun Xu¹, Lujun Zhang¹, Guangqi Jiang¹, Yining Hua², Yi Liu^1,*

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 3021-3039, 2024, DOI:10.32604/cmc.2023.045853

Abstract This paper focuses on the task of few-shot 3D point cloud semantic segmentation. Despite some progress, this task still encounters many issues due to the insufficient samples given, e.g., incomplete object segmentation and inaccurate semantic discrimination. To tackle these issues, we first leverage part-whole relationships into the task of 3D point cloud semantic segmentation to capture semantic integrity, which is empowered by the dynamic capsule routing with the module of 3D Capsule Networks (CapsNets) in the embedding network. Concretely, the dynamic routing amalgamates geometric information of the 3D point cloud data to construct higher-level feature representations, which capture the relationships… More >

Yanzhao Zhou, Binghao Liu, Yiran Liu, Jianbin Jiao^*

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.1, pp. 647-668, 2023, DOI:10.32604/cmes.2023.026745

Abstract Deep Convolution Neural Networks (DCNNs) can capture discriminative features from large datasets. However, how to incrementally learn new samples without forgetting old ones and recognize novel classes that arise in the dynamically changing world, e.g., classifying newly discovered fish species, remains an open problem. We address an even more challenging and realistic setting of this problem where new class samples are insufficient, i.e., Few-Shot Class-Incremental Learning (FSCIL). Current FSCIL methods augment the training data to alleviate the overfitting of novel classes. By contrast, we propose Filter Bank Networks (FBNs) that augment the learnable filters to capture fine-detailed features for adapting… More >

Qaisar Abbas¹, Abdul Rauf Baig^1,*, Ayyaz Hussain²

CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 1483-1499, 2023, DOI:10.32604/cmc.2023.036366

Abstract The diagnosis of eye disease through deep learning (DL) technology is the latest trend in the field of artificial intelligence (AI). Especially in diagnosing pathologic myopia (PM) lesions, the implementation of DL is a difficult task because of the classification complexity and definition system of PM. However, it is possible to design an AI-based technique that can identify PM automatically and help doctors make relevant decisions. To achieve this objective, it is important to have adequate resources such as a high-quality PM image dataset and an expert team. The primary aim of this research is to design and train the… More >

Yuncong Peng^1,2, Xiaolin Qin^1,2,*, Qianlei Wang^1,2, Boyi Fu^1,2, Yongxiang Gu^1,2

Computer Systems Science and Engineering, Vol.46, No.1, pp. 1233-1247, 2023, DOI:10.32604/csse.2023.032633

Abstract At present, deep learning has been well applied in many fields. However, due to the high complexity of hypothesis space, numerous training samples are usually required to ensure the reliability of minimizing experience risk. Therefore, training a classifier with a small number of training examples is a challenging task. From a biological point of view, based on the assumption that rich prior knowledge and analogical association should enable human beings to quickly distinguish novel things from a few or even one example, we proposed a dynamic analogical association algorithm to make the model use only a few labeled samples for… More >

YUHAN JI¹, YONG LIANG^1,*, ZIYI YANG², NING AI¹

BIOCELL, Vol.47, No.3, pp. 569-579, 2023, DOI:10.32604/biocell.2023.025865

Abstract Few-shot learning is becoming more and more popular in many fields, especially in the computer vision field. This inspires us to introduce few-shot learning to the genomic field, which faces a typical few-shot problem because some tasks only have a limited number of samples with high-dimensions. The goal of this study was to investigate the few-shot disease sub-type prediction problem and identify patient subgroups through training on small data. Accurate disease sub-type classification allows clinicians to efficiently deliver investigations and interventions in clinical practice. We propose the SW-Net, which simulates the clinical process of extracting the shared knowledge from a… More >

Dengyong Zhang^1,2, Huaijian Pu^1,2, Feng Li^1,2,*, Xiangling Ding³, Victor S. Sheng⁴

CMC-Computers, Materials & Continua, Vol.74, No.2, pp. 3439-3454, 2023, DOI:10.32604/cmc.2023.027267

Abstract Now object detection based on deep learning tries different strategies. It uses fewer data training networks to achieve the effect of large dataset training. However, the existing methods usually do not achieve the balance between network parameters and training data. It makes the information provided by a small amount of picture data insufficient to optimize model parameters, resulting in unsatisfactory detection results. To improve the accuracy of few shot object detection, this paper proposes a network based on the transformer and high-resolution feature extraction (THR). High-resolution feature extraction maintains the resolution representation of the image. Channels and spatial attention are… More >

Nagwa Elaraby^*, Sherif Barakat, Amira Rezk

CMC-Computers, Materials & Continua, Vol.74, No.1, pp. 1837-1854, 2023, DOI:10.32604/cmc.2023.032288

Abstract Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks. It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks (CNNs) for learning a distance function that can map input data from the input space to the feature space. Instead of determining the class of each sample, the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not. The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly… More >

Xiaoyu^1,2, Tian Zhenzhen², Xin Zihao², Liu Suolan², Chen Fuhua³, Wang Hongyuan^2,*

Journal of New Media, Vol.4, No.3, pp. 137-143, 2022, DOI:10.32604/jnm.2022.027890

Abstract Recent advances in OCR show that end-to-end (E2E) training pipelines including detection and identification can achieve the best results. However, many existing methods usually focus on case insensitive English characters. In this paper, we apply an E2E approach, the multiplex multilingual mask TextSpotter, which performs script recognition at the word level and uses different recognition headers to process different scripts while maintaining uniform loss, thus optimizing script recognition and multiple recognition headers simultaneously. Experiments show that this method is superior to the single-head model with similar number of parameters in end-to-end identification tasks. More >

Zengchen Yu¹, Ke Wang^2,*, Shuxuan Xie¹, Yuanfeng Zhong¹, Zhihan Lv³

CMES-Computer Modeling in Engineering & Sciences, Vol.131, No.2, pp. 655-675, 2022, DOI: 10.32604/cmes.2022.019612

Abstract Few-shot Learning algorithms can be effectively applied to fields where certain categories have only a small amount of data or a small amount of labeled data, such as medical images, terrorist surveillance, and so on. The Metric Learning in the Few-shot Learning algorithm is classified by measuring the similarity between the classified samples and the unclassified samples. This paper improves the Prototypical Network in the Metric Learning, and changes its core metric function to Manhattan distance. The Convolutional Neural Network of the embedded module is changed, and mechanisms such as average pooling and Dropout are added. Through comparative experiments, it… More >