Table 1 The overall classification accuracy (%) on the AHE database using different backbone network

From: Dual-stream multi-layer cross encoding network for texture analysis of architectural heritage elements

Backbone network

DMCE-Net

Intra-layer encoding stream

Inter-layer encoding stream

VGG-VD19

95.27 ± 0.004

95.05 ± 0.004

92.93 ± 0.005

VGG-VD16

95.36 ± 0.004

95.16 ± 0.004

93.84 ± 0.005

AlexNet

93.99 ± 0.004

93.91 ± 0.005

92.95 ± 0.005