arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.08697cs.CV
收藏

通过完形理论理解深度卷积网络

Understanding Deep Convolutional Networks through Gestalt Theory

Democritus University of Thrace(色雷斯德谟克利特大学);EMaTTech

Angelos Amanatiadis, Vasileios Kaburlasos, Elias Kosmatopoulos

摘要:

深度卷积网络在高维问题上的卓越性能使它们在几个应用中非常受欢迎。尽管它们被广泛采用,但其基本机制仍然不清楚,其改进程序仍然主要依赖于试错过程。我们引入了一种新的灵敏度分析的基础上的格式塔理论,使深入了解分类功能和中间层。由于格式塔心理学规定,感知可以是几个元素之间复杂的相互作用的产物,我们进行了基于这个概念的消融研究,发现哪些原则和图像上下文显着有助于网络分类。我们的研究结果表明,ConvNets在几个层面上遵循完形原则定义的大多数视觉皮层感知机制。所提出的框架刺激分类问题中的特定特征图,并揭示重要的网络属性,从而产生更可解释的网络模型。

英文摘要:

The superior performance of deep convolutional networks over high-dimensional problems have made them very popular for several applications. Despite their wide adoption, their underlying mechanisms still remain unclear with their improvement procedures still relying mainly on a trial and error process. We introduce a novel sensitivity analysis based on the Gestalt theory for giving insights into the classifier function and intermediate layers. Since Gestalt psychology stipulates that perception can be a product of complex interactions among several elements, we perform an ablation study based on this concept to discover which principles and image context significantly contribute in the network classification. Our results reveal that ConvNets follow most of the visual cortical perceptual mechanisms defined by the Gestalt principles at several levels. The proposed framework stimulates specific feature maps in classification problems and reveal important network attributes that can produce more explainable network 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。

↑