作者: Vincent Christlein , Mathias Seuret , Pavel Král , Anguelos Nicolaou , Andreas Maier
DOI:
关键词: Artificial intelligence 、 Identification (information) 、 Pattern recognition 、 Computer science 、 Convolutional neural network 、 Pooling 、 Aggregate (data warehouse) 、 Max pooling 、 Layer (object-oriented design) 、 Contrast (statistics)
摘要: Global pooling layers are an essential part of Convolutional Neural Networks (CNN). They are used to aggregate activations of spatial locations to produce a fixed-size vector in several …