arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.14722q-bio.OTeess.IV
收藏

CNN与Transformer模型在透射电子显微镜多类病毒分类中的比较与混合研究

A Comparative and Hybrid Study of CNN and Transformer Models for Multi-Class Virus Classification in Transmission Electron Microscopy

CCN University of Science and Technology(CCN科学与技术大学);Deakin University(迪肯大学);American International University-Bangladesh(孟加拉美国国际大学);Asian University of Bangladesh(孟加拉亚洲大学);Magura polytechnic Institute(马古拉理工学院);Khulna University of Engineering & Technology (KUET)(库尔纳工程与技术大学)

Md Mahmudul Hoque, Md Kawser Islam, Md. Mamunur Rahman Moon, Abdullah Rakib Akand, Md. Hadi Al-amin, H. M. Azrof

AI总结:

本研究比较了CNN和Transformer模型在TEM图像中22类病毒分类的性能,通过加权交叉熵缓解类别不平衡,Swin Transformer表现最佳,混合策略进一步提升了宏F1分数。

摘要:

在透射电子显微镜(TEM)图像中自动识别病毒颗粒仍然是一项艰巨的任务,主要由于强类间相似性、尺度变异和显著的类别不平衡。本研究使用TEM病毒数据集,比较评估了多种卷积神经网络和基于Transformer的架构在22个病毒类别分类中的性能。所有模型在相同的预处理和优化条件下训练,并通过加权交叉熵公式缓解不平衡效应。性能通过总体准确率以及宏平均精确率、召回率和F1分数进行量化。在独立模型中,Swin Transformer取得了最高准确率(0.8831)和宏F1分数(0.8444),其次是DeiT(准确率0.8669)。卷积架构表现出相对较低的平衡性能,其中ResNet50在不平衡条件下显著退化(准确率0.5887)。为了利用互补的表示特性,实现了决策级混合策略。性能加权混合达到了0.8831的准确率和最高的宏F1分数(0.8528),略优于等权混合配置。这些观察表明,架构异质性有助于改善类间平衡而不牺牲整体预测准确性。未来工作可以探索尺度感知表示、特征级融合机制和扩展的TEM数据集,以进一步增强病毒识别任务的鲁棒性和泛化能力。

英文摘要:

The automatic recognition of virus particles in transmission electron microscopy (TEM) images remains a demanding task, primarily owing to strong inter-class similarity, scale variability, and pronounced class imbalance. In this study, several convolutional neural networks and transformer-based architectures were comparatively evaluated for the classification of 22 virus categories using the TEM virus dataset. All models were trained under identical preprocessing and optimization conditions, and imbalance effects were mitigated through a weighted cross-entropy formulation. Performance was quantified using overall accuracy together with macro-averaged precision, recall, and F1 score. Among standalone models, the Swin Transformer achieved the highest accuracy (0.8831) and macro-F1 score (0.8444), followed by DeiT (accuracy 0.8669). Convolutional architectures exhibited comparatively lower balanced performance, with ResNet50 demonstrating substantial degradation (accuracy 0.5887) under imbalanced conditions. To exploit complementary representational properties, decision-level hybrid strategies were implemented. The performance-weighted hybrid attained an accuracy of 0.8831 and the highest macro-F1 score (0.8528), slightly surpassing the equal-weight hybrid configuration. These observations indicate that architectural heterogeneity contributes to improved inter-class balance without sacrificing overall predictive accuracy. Future work may explore scale-aware representations, feature-level fusion mechanisms, and expanded TEM datasets to further enhance robustness and generalization in virus identification tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑