一项新近发表在arXiv上的研究，为轻量级卷积神经网络（CNNs）提供了一个可复现的基准测试。该研究在CIFAR-10、CIFAR-100和Tiny ImageNet数据集上比较了七种已建立的架构。研究人员在统一的微调协议下，根据准确性、参数数量、存储和计算操作评估了模型。EfficientNetV2-S取得了最高的Top-1准确率，而EfficientNet-B0在性能和效率之间取得了良好的平衡，使用的参数和操作数量显著减少。研究还强调了ImageNet预训练的巨大优势，尤其是在CIFAR-100和Tiny ImageNet等较大的数据集上。 AI
影响 为选择高效的卷积神经网络提供了清晰的参考，有助于开发人员在资源受限的环境中进行选择。
排序理由 学术论文，详细介绍了现有模型的基准比较。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packa…
Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet …
arXiv:2505.03303v3 Announce Type: replace-cross Abstract: Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to inte…