Left-Right Skip-DenseNets for Coarse-to-Fine Object Categorization

10/28/2017

∙

by   Changmao Cheng, et al.

∙

0

∙

share

Inspired by the recent neuroscience studies on the left-right asymmetry of the brains in the low and high spatial frequency processing, we introduce a novel type of network -- the left-right skip-densenets for coarse-to-fine object categorization. This network can enable both coarse and fine-grained classification in a single framework. We also for the first time propose the layer-skipping mechanism which learns a gating network to predict whether skip some layers in the testing stage. This layer-skipping mechanism assigns more flexibility and capability to our network for the categorization tasks. Our network is evaluated on three widely used datasets; the results show that our network is more promising in solving the coarse-to-fine object categorization than the competitors.