CSPResNeXt
2000년 도입 · 논문 3편에서 사용
CSPResNeXt is a convolutional neural network where we apply the Cross Stage Partial Network (CSPNet) approach to ResNeXt. The CSPNet partitions the feature map of the base layer into two parts and then merges them through a cross-stage hierarchy. The use of a split and merge strategy allows for more gradient flow through the network.
출처: CSPNet: A New Backbone that can Enhance Learning Capability of CNN
소개 논문: CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Convolutional Neural Networks · Computer Vision