arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.11989cs.CVcs.AI
收藏

深度神经网络在图像分类中的迁移学习评估

A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Computer Science Institute, Ruhr West University of Applied Sciences, 46236 Bottrop(鲁尔西大学应用科学学院计算机科学研究所)

Nermeen Abou Baker, Nico Zengeler, Uwe Handmann

AI总结:

本文研究如何选择最佳预训练模型以满足图像分类任务需求,通过优化输出层和网络参数,将11种ImageNet预训练模型知识应用于5个目标数据集,评估模型在单次训练和十次训练中的准确性、准确率密度、训练时间和模型大小。

摘要:

迁移学习是一种机器学习技术,通过在源领域获得的知识来增强目标领域的学习,通过重用已学习的权重。这种技术普及是因为其在实现高性能的同时节省训练时间、内存和网络设计的努力。本文研究如何选择最佳预训练模型以满足图像分类任务的需求。在我们的研究中,我们优化了输出层和通用网络参数,将11种在ImageNet上预训练的图像处理模型的知识应用于五个不同的目标领域数据集。我们测量了准确性、准确性密度、训练时间和模型大小,以评估预训练模型在一次训练会话和十次训练会话中的表现。

英文摘要:

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.

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。

↑