all AI news
S$^2$-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation. (arXiv:2206.07298v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Modern high-performance semantic segmentation methods employ a heavy backbone
and dilated convolution to extract the relevant feature. Although extracting
features with both contextual and semantic information is critical for the
segmentation tasks, it brings a memory footprint and high computation cost for
real-time applications. This paper presents a new model to achieve a trade-off
between accuracy/speed for real-time road scene semantic segmentation.
Specifically, we proposed a lightweight model named Scale-aware Strip Attention
Guided Feature Pyramid Network (S$^2$-FPN). Our network consists …
arxiv attention cv feature network real-time scale segmentation semantic time