Kernelized dynamic convolution routing in spatial and channel interaction for attentive concrete defect recognition

作者：

Highlights：

• CSDNet embeds novel SCA module to apportion higher weightage in defective regions.

• KSF encoder captures complex visual features using kernelized convolution.

• KSF encoder aggregates robust features using dynamic convolution routing. Extensive experimentation on four datasets shows superiority of our proposed network.

摘要

•CSDNet embeds novel SCA module to apportion higher weightage in defective regions.•KSF encoder captures complex visual features using kernelized convolution.•KSF encoder aggregates robust features using dynamic convolution routing. Extensive experimentation on four datasets shows superiority of our proposed network.

论文关键词：Kernel salient feature encoder,Spatial-channel attention,Concrete structural defect,Convolutional neural network,Multi-target multi-class classification

论文评审过程：Received 13 July 2021, Revised 19 May 2022, Accepted 8 July 2022, Available online 18 July 2022, Version of Record 21 July 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116818