Skip Connection Blocks

CSPResNeXt Block

Introduced by Wang et al. in CSPNet: A New Backbone that can Enhance Learning Capability of CNN

CSPResNeXt Block is an extended ResNext Block where we partition the feature map of the base layer into two parts and then merge them through a cross-stage hierarchy. The use of a split and merge strategy allows for more gradient flow through the network.

Source: CSPNet: A New Backbone that can Enhance Learning Capability of CNN

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Object Detection 2 33.33%
Real-Time Object Detection 2 33.33%
BIG-bench Machine Learning 1 16.67%
Image Classification 1 16.67%

Categories