.png){kind=icon}
返回
Image Style Classification Based on Learnt Deep Correlation Features
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2018.2801718.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a comprehensive study of deep correlation features on image style classification. Inspired by that, correlation between feature maps can effectively describe image texture, and we design various correlations and transform them into style vectors, and investigate classification performance brought by different variants. In addition to intralayer correlation, interlayer correlation is proposed as well, and its effectiveness is verified. After showing the effectiveness of deep correlation features, we further propose a learning framework to automatically learn correlations between feature maps. Through extensive experiments on image style classification and artist classification, we demonstrate that the proposed learnt deep correlation features outperform several variants of convolutional neural network features by a large margin, and achieve the state-of-the-art performance.
Keyword:
Painting images
convolutional neural network
Gram matrix
deep correlation features
learnt correlation features
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.7
论文数:
5.2K
被引数:
2.6W
机构
引用论文
ARVino - outdoor augmented reality visualisation of viticulture GIS dataARVino-葡萄栽培GIS数据的户外增强现实可视化
OAAI
.png){kind=icon}
OAAI分享收藏
Vitreous Hemorrhage following Phakic Anterior Chamber Intraocular Lens Implantation in Severe Myopia
PREAI
分享收藏
查看更多内容