当前位置:
X-MOL 学术
›
arXiv.cs.CV
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-04-06 , DOI: arxiv-2004.03015 Qiuyu Chen, Wei Zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, Jianping Fan
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-04-06 , DOI: arxiv-2004.03015 Qiuyu Chen, Wei Zhang, Ning Zhou, Peng Lei, Yi Xu, Yu Zheng, Jianping Fan
To leverage deep learning for image aesthetics assessment, one critical but
unsolved issue is how to seamlessly incorporate the information of image aspect
ratios to learn more robust models. In this paper, an adaptive fractional
dilated convolution (AFDC), which is aspect-ratio-embedded,
composition-preserving and parameter-free, is developed to tackle this issue
natively in convolutional kernel level. Specifically, the fractional dilated
kernel is adaptively constructed according to the image aspect ratios, where
the interpolation of nearest two integers dilated kernels is used to cope with
the misalignment of fractional sampling. Moreover, we provide a concise
formulation for mini-batch training and utilize a grouping strategy to reduce
computational overhead. As a result, it can be easily implemented by common
deep learning libraries and plugged into popular CNN architectures in a
computation-efficient manner. Our experimental results demonstrate that our
proposed method achieves state-of-the-art performance on image aesthetics
assessment over the AVA dataset.
中文翻译:
用于图像美学评估的自适应分数扩张卷积网络
为了利用深度学习进行图像美学评估,一个关键但尚未解决的问题是如何无缝整合图像纵横比信息以学习更强大的模型。在本文中,开发了一种自适应分数扩张卷积 (AFDC),它是嵌入纵横比、保留成分和无参数的,以在卷积内核级别本地解决这个问题。具体而言,分数扩张核是根据图像纵横比自适应构建的,其中最近两个整数扩张核的插值用于应对分数采样的错位。此外,我们为小批量训练提供了简洁的公式,并利用分组策略来减少计算开销。因此,它可以通过常见的深度学习库轻松实现,并以计算效率高的方式插入流行的 CNN 架构。我们的实验结果表明,我们提出的方法在 AVA 数据集上实现了最先进的图像美学评估性能。
更新日期:2020-04-08
中文翻译:
用于图像美学评估的自适应分数扩张卷积网络
为了利用深度学习进行图像美学评估,一个关键但尚未解决的问题是如何无缝整合图像纵横比信息以学习更强大的模型。在本文中,开发了一种自适应分数扩张卷积 (AFDC),它是嵌入纵横比、保留成分和无参数的,以在卷积内核级别本地解决这个问题。具体而言,分数扩张核是根据图像纵横比自适应构建的,其中最近两个整数扩张核的插值用于应对分数采样的错位。此外,我们为小批量训练提供了简洁的公式,并利用分组策略来减少计算开销。因此,它可以通过常见的深度学习库轻松实现,并以计算效率高的方式插入流行的 CNN 架构。我们的实验结果表明,我们提出的方法在 AVA 数据集上实现了最先进的图像美学评估性能。