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 2203.16031cs.CVcs.LG
收藏

你的艺术有多深:单任务、单模态神经网络艺术理解极限的实验研究

How Deep is Your Art: An Experimental Study on the Limits of Artistic Understanding in a Single-Task, Single-Modality Neural Network

Stony Brook University(石溪大学);Texas Tech University(德克萨斯理工大学);Regis College(瑞吉斯学院)

Mahan Agha Zahedi, Niloofar Gholamrezaei, Alex Doboli

AI总结:

本文用VGG-11在概念摄影画廊数据集上测试DCNN,证明其仅依赖形状、颜色等外显属性分类艺术作品,而无法利用历史背景与艺术家意图等非外显属性。

摘要:

艺术品意义的计算建模复杂而困难,这是因为艺术解读具有多维度且高度主观性。本文通过实验考察了一种最先进的深度卷积神经网络(DCNN)——一种流行的机器学习方法——在多大程度上能够正确地将现代概念艺术作品区分到艺术策展人设计的画廊中。研究提出两个假设,指出DCNN模型在分类时使用形状和颜色等外显属性,而不使用历史背景和艺术家意图等非外显属性。为此设计的方法对这两个假设进行了实验验证。研究使用在ImageNet数据集上预训练并经过判别式微调的VGG-11 DCNN,在由真实世界概念摄影画廊构建的手工数据集上进行训练。实验结果支持这两个假设,表明DCNN模型忽略非外显属性,并且仅使用外显属性进行艺术品分类。本工作指出了当前DCNN的局限性,未来的DNN模型应当解决这些问题。

英文摘要:

Computational modeling of artwork meaning is complex and difficult. This is because art interpretation is multidimensional and highly subjective. This paper experimentally investigated the degree to which a state-of-the-art Deep Convolutional Neural Network (DCNN), a popular Machine Learning approach, can correctly distinguish modern conceptual art work into the galleries devised by art curators. Two hypotheses were proposed to state that the DCNN model uses Exhibited Properties for classification, like shape and color, but not Non-Exhibited Properties, such as historical context and artist intention. The two hypotheses were experimentally validated using a methodology designed for this purpose. VGG-11 DCNN pre-trained on ImageNet dataset and discriminatively fine-tuned was trained on handcrafted datasets designed from real-world conceptual photography galleries. Experimental results supported the two hypotheses showing that the DCNN model ignores Non-Exhibited Properties and uses only Exhibited Properties for artwork classification. This work points to current DCNN limitations, which should be addressed by future DNN models.

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。

↑