DeepScene: Scene classification via convolutional neural network with spatial pyramid pooling

作者：

Highlights：

• Deep neural network-based style transfer for colorization of grayscale images.

• CNN with SPP to enable multi-size training for scale and translational invariance.

• Weighted average ensemble to improve the performance in scene classification.

• Model regularization by dropout and Ridge regression.

摘要

•Deep neural network-based style transfer for colorization of grayscale images.•CNN with SPP to enable multi-size training for scale and translational invariance.•Weighted average ensemble to improve the performance in scene classification.•Model regularization by dropout and Ridge regression.

论文关键词：Scene classification,Convolutional neural network,Spatial pyramid pooling,Style transfer

论文评审过程：Received 13 April 2021, Revised 27 August 2021, Accepted 5 December 2021, Available online 24 December 2021, Version of Record 6 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116382