ResFeats: Residual network based features for underwater image classification

作者：

Highlights：

• Introduction of ResFeats (features extracted from deep residual network)

• Application of ResFeats to underwater image classification

• Combining ResFeats from different layers for improved performance

• Superior classification performance over previous CNN features

• State-of-the-art results on four marine datasets

摘要

•Introduction of ResFeats (features extracted from deep residual network)•Application of ResFeats to underwater image classification•Combining ResFeats from different layers for improved performance•Superior classification performance over previous CNN features•State-of-the-art results on four marine datasets

论文关键词：Deep learning,Residual networks,Deep features,Image classification,Underwater image classification

论文评审过程：Received 2 August 2018, Revised 13 September 2019, Accepted 16 September 2019, Available online 1 November 2019, Version of Record 21 January 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.09.002