A full data augmentation pipeline for small object detection based on generative adversarial networks

作者：

Highlights：

• Full pipeline for data augmentation for small object detection.

• High-quality synthetic data combining a GAN with image inpainting and blending.

• DS-GAN generates realistic small objects from larger ones.

摘要

•Full pipeline for data augmentation for small object detection.•High-quality synthetic data combining a GAN with image inpainting and blending.•DS-GAN generates realistic small objects from larger ones.

论文关键词：Small object detection,Data augmentation,Generative adversarial network

论文评审过程：Received 9 February 2022, Revised 27 July 2022, Accepted 20 August 2022, Available online 31 August 2022, Version of Record 8 September 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108998