对比11个预训练模型，选出最适合图像分类任务的迁移学习方案。
A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
- 用ImageNet预训练的11个模型迁移至5个新数据集
- 在单次和十次训练中均验证准确率与效率
- 适合需要快速部署模型的研究者参考
迁移学习通过复用源域学习到的权重，提升目标域的学习效果，具有高效省时、节省内存的优势。本文研究如何为图像分类任务选择最适配目标域的预训练模型。我们对11个在ImageNet上预训练的图像处理模型，调整输出层和通用网络参数，应用于5个不同目标数据集。通过测量准确率、准确率密度、训练时间与模型大小，在单次训练和十次训练实验中评估各模型表现。
原文摘要 · Abstract (English)
Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.
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。