GPNet: Gated pyramid network for semantic segmentation

作者：

Highlights：

• Propose a gated pyramid module to incorporate both low-level and high-level features.

• Apply gated path to filter the useful feature and obtain robust semantic context.

• Propose the cross-layer attention module to further exploit context from shallow layers.

• Refine the noisy upsampled features and retain the spatial context by using cross-layer attentions.

摘要

•Propose a gated pyramid module to incorporate both low-level and high-level features.•Apply gated path to filter the useful feature and obtain robust semantic context.•Propose the cross-layer attention module to further exploit context from shallow layers.•Refine the noisy upsampled features and retain the spatial context by using cross-layer attentions.

论文关键词：Deep learning,Semantic segmentation,Context embedding,Gated mechanism,Attention

论文评审过程：Received 3 June 2020, Revised 13 February 2021, Accepted 5 March 2021, Available online 11 March 2021, Version of Record 24 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107940