Few-shot traffic sign recognition with clustering inductive bias and random neural network

作者：

Highlights：

• A novel generative feature learning framework for TSR is proposed with clustering inductive bias.

• Clustering-oriented feature mapping is learned based on a novel random neural network.

• Computationally efficient feature mapping can be achieved with a fast Gaussian random projection.

摘要

•A novel generative feature learning framework for TSR is proposed with clustering inductive bias.•Clustering-oriented feature mapping is learned based on a novel random neural network.•Computationally efficient feature mapping can be achieved with a fast Gaussian random projection.

论文关键词：Traffic sign recognition,Few-shot learning,Clustering,Randomization,

论文评审过程：Received 31 May 2019, Revised 2 December 2019, Accepted 11 December 2019, Available online 14 December 2019, Version of Record 13 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107160