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 2011.02727cs.CV
收藏

艺术图像卷积神经网络的迁移学习分析

An analysis of the transfer learning of convolutional neural networks for artistic images

Télécom Paris(巴黎高等电信学院);Institut Polytechnique de Paris(巴黎理工学院);Université Paris Saclay(巴黎萨克雷大学)

Nicolas Gonthier, Yann Gousseau, Saïd Ladjal

摘要:

从巨大的自然图像数据集进行迁移学习、深度神经网络的微调以及相应的预训练网络的使用实际上已经成为艺术分析应用的核心。然而,迁移学习的效果仍然知之甚少。在本文中,我们首先使用可视化网络内部表示的技术,以便为理解网络在艺术图像上学到的东西提供线索。然后,我们提供了一个定量分析的学习过程中引入的变化,由于在特征和参数空间的度量,以及在最大激活图像集上计算的度量。这些分析是在迁移学习过程的几种变化上进行的。特别是,我们观察到网络可以将一些预先训练的过滤器专门用于新的图像模态,并且更高层倾向于集中类。最后,我们已经证明,即使任务发生变化,涉及中等大小艺术数据集的双重微调也可以改善较小数据集的分类。

英文摘要:

Transfer learning from huge natural image datasets, fine-tuning of deep neural networks and the use of the corresponding pre-trained networks have become de facto the core of art analysis applications. Nevertheless, the effects of transfer learning are still poorly understood. In this paper, we first use techniques for visualizing the network internal representations in order to provide clues to the understanding of what the network has learned on artistic images. Then, we provide a quantitative analysis of the changes introduced by the learning process thanks to metrics in both the feature and parameter spaces, as well as metrics computed on the set of maximal activation images. These analyses are performed on several variations of the transfer learning procedure. In particular, we observed that the network could specialize some pre-trained filters to the new image modality and also that higher layers tend to concentrate classes. Finally, we have shown that a double fine-tuning involving a medium-size artistic dataset can improve the classification on smaller datasets, even when the task changes.

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。

↑