A survey and performance evaluation of deep learning methods for small object detection

作者：

Highlights：

• Review of state-of-the-art deep learning techniques on small object detection.

• Summarize major components of deep learning methods and categorize existing methods.

• Identify challenges and solutions for small object detection in four aspects.

• Empirical performance evaluation on state-of-the-art deep learning methods.

摘要

•Review of state-of-the-art deep learning techniques on small object detection.•Summarize major components of deep learning methods and categorize existing methods.•Identify challenges and solutions for small object detection in four aspects.•Empirical performance evaluation on state-of-the-art deep learning methods.

论文关键词：Small object detection,Computer vision,Convolutional neural networks,Deep learning

论文评审过程：Received 9 April 2020, Revised 13 October 2020, Accepted 10 January 2021, Available online 19 January 2021, Version of Record 5 February 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114602