Brain-Inspired Deep Networks for Image Aesthetics Assessment
Brain-Inspired Deep Networks for Image Aesthetics Assessment
复制标题
DOI：
--
复制
发表时间：
2016-01
期刊：
影响因子：
--
通讯作者：
Zhangyang Wang;F. Dolcos;D. Beck;Shiyu Chang;Thomas S. Huang
中科院分区：
文献类型：
--
作者：
Zhangyang Wang;F. Dolcos;D. Beck;Shiyu Chang;Thomas S. Huang
图像美学评价因其主观性而具有挑战性。受人类视觉感知和神经美学的科学进步的启发，我们设计了大脑启发的深度网络（BDN）来完成这项任务。BDN首先通过并行监督路径学习属性，在各种选定的特征维度上。训练一个高级合成网络，将这些属性关联并转换为整体美学评级。然后，我们将BDN扩展到预测人类评级的分布，因为美学评级往往是主观的。另一个亮点是我们首次在美学评估的背景下研究了标签保持转换，这导致了一种有效的数据增强方法。在AVA数据集上的实验结果表明，与具有相同或更高参数容量的其他最先进的模型相比，我们的生物启发和特定任务的BDN模型获得了显着的性能改善。
Image aesthetics assessment has been challenging due to its subjective nature. Inspired by the scientific advances in the human visual perception and neuroaesthetics, we design Brain-Inspired Deep Networks (BDN) for this task. BDN first learns attributes through the parallel supervised pathways, on a variety of selected feature dimensions. A high-level synthesis network is trained to associate and transform those attributes into the overall aesthetics rating. We then extend BDN to predicting the distribution of human ratings, since aesthetics ratings are often subjective. Another highlight is our first-of-its-kind study of label-preserving transformations in the context of aesthetics assessment, which leads to an effective data augmentation approach. Experimental results on the AVA dataset show that our biological inspired and task-specific BDN model gains significantly performance improvement, compared to other state-of-the-art models with the same or higher parameter capacity.