对比自研与预训练模型在孟加拉数据集上的表现，揭示性能与效率权衡。
Performance Analysis of Image Classification on Bangladeshi Datasets
- 在相同条件下比较自研CNN与VGG-16、ResNet-50、MobileNet的分类效果。
- 预训练模型在小数据下准确率更高，收敛更快，但参数更多。
- 自研模型参数少、计算量低，适合资源受限场景。
卷积神经网络（CNN）在图像分类任务中表现出色，但自建模型与使用预训练架构的选择仍是关键实践问题。本文对自研设计的CNN与VGG-16、ResNet-50、MobileNet等主流深度学习模型进行对比分析。自研CNN从头训练，而预训练模型采用迁移学习，在相同实验设置下评估。所有模型均使用准确率、精确率、召回率和F1分数等标准指标进行评价。实验表明，预训练架构在训练数据有限时，分类准确率和收敛速度均优于自研模型；然而，自研模型参数显著更少，计算复杂度更低，具备竞争力。研究揭示了模型复杂度、性能与计算效率之间的权衡，为图像分类任务中的架构选择提供了实用指导。
原文摘要 · Abstract (English)
Convolutional Neural Networks (CNNs) have demonstrated remarkable success in image classification tasks; however, the choice between designing a custom CNN from scratch and employing established pre-trained architectures remains an important practical consideration. In this work, we present a comparative analysis of a custom-designed CNN and several widely used deep learning architectures, including VGG-16, ResNet-50, and MobileNet, for an image classification task. The custom CNN is developed and trained from scratch, while the popular architectures are employed using transfer learning under identical experimental settings. All models are evaluated using standard performance metrics such as accuracy, precision, recall, and F1-score. Experimental results show that pre-trained CNN architectures consistently outperform the custom CNN in terms of classification accuracy and convergence speed, particularly when training data is limited. However, the custom CNN demonstrates competitive performance with significantly fewer parameters and reduced computational complexity. This study highlights the trade-offs between model complexity, performance, and computational efficiency, and provides practical insights into selecting appropriate CNN architectures for image classification problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。