DFAEN: Double-order knowledge fusion and attentional encoding network for texture recognition

作者：

Highlights：

• A deep multi-order texture encoding end-to-end network is proposed.

• Attention-based texture encoding mechanism for texture representation learning.

• The double orders information is modeled effectively in encoding learning stage.

• Our approach achieves excellent experimental results in five challenging datasets.

摘要

•A deep multi-order texture encoding end-to-end network is proposed.•Attention-based texture encoding mechanism for texture representation learning.•The double orders information is modeled effectively in encoding learning stage.•Our approach achieves excellent experimental results in five challenging datasets.

论文关键词：Deep learning,Information fusion,Attentional mechanism,Texture recognition

论文评审过程：Received 26 January 2022, Revised 10 April 2022, Accepted 17 July 2022, Available online 25 July 2022, Version of Record 6 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118223