A review on 2D instance segmentation based on deep neural networks

作者：

Highlights：

• Review representative instance segmentation methods.

• Describe common instance segmentation benchmark datasets and evaluation metrics.

• Present the evaluation results of different instance segmentation methods.

• Delineate representative CNN-based and Transformer-based backbones in instance segmentation methods.

• Discuss future research directions of instance segmentation.

摘要

•Review representative instance segmentation methods.•Describe common instance segmentation benchmark datasets and evaluation metrics.•Present the evaluation results of different instance segmentation methods.•Delineate representative CNN-based and Transformer-based backbones in instance segmentation methods.•Discuss future research directions of instance segmentation.

论文关键词：Instance segmentation,Deep neural networks,Computer vision,Review

论文评审过程：Received 1 November 2021, Revised 28 January 2022, Accepted 1 February 2022, Available online 5 February 2022, Version of Record 15 February 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104401