A hierarchical sampling based triplet network for fine-grained image classification

作者：

Highlights：

• Building layered ontology for 3 different databases to guide the layered knowledge of the network.

• Hierarchical sampling method for mining more effective hard triplets to get better performance.

• Acquisition of more discriminative deep feature by building hierarchical structure with semantic knowledge.

• Combination of hierarchical structure and triplet loss to construct a layered Triplet loss function.

摘要

•Building layered ontology for 3 different databases to guide the layered knowledge of the network.•Hierarchical sampling method for mining more effective hard triplets to get better performance.•Acquisition of more discriminative deep feature by building hierarchical structure with semantic knowledge.•Combination of hierarchical structure and triplet loss to construct a layered Triplet loss function.

论文关键词：Metric learning,Triplet network,Layered ontology,Layered triplet loss,Multi-task learning

论文评审过程：Received 27 February 2020, Revised 25 January 2021, Accepted 8 February 2021, Available online 13 February 2021, Version of Record 26 February 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107889