Efficient semantic segmentation with pyramidal fusion

作者：

Highlights：

• We present pyramidal fusion: a principled approach for dense recognition based on resolution pyramids.

• Our pyramidal model outperforms all previous semantic segmentation approaches aiming at real-time operation.

• It achieves 76.4% mIoU on Cityscapes test by processing 2MPx images at 34 Hz on GTX 1080 Ti.

• Our model acts as an ensemble of shallow models with a large effective receptive field.

摘要

•We present pyramidal fusion: a principled approach for dense recognition based on resolution pyramids.•Our pyramidal model outperforms all previous semantic segmentation approaches aiming at real-time operation.•It achieves 76.4% mIoU on Cityscapes test by processing 2MPx images at 34 Hz on GTX 1080 Ti.•Our model acts as an ensemble of shallow models with a large effective receptive field.

论文关键词：Semantic segmentation,Real-time inference,Shared resolution pyramid,Computer vision,Deep learning

论文评审过程：Received 28 July 2019, Revised 20 July 2020, Accepted 19 August 2020, Available online 20 August 2020, Version of Record 1 November 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107611