PaperBMVC 2019 (arXiv 2019) · 2019
Fast-SCNN: Fast Semantic Segmentation Network
1page built on it
0more pages cite it
1narrative
0registry papers cite it
In the Atlas
ModelPrimary source of
Fast-SCNN
Real-time semantic segmentation CNN whose shared shallow 'Learning to Downsample' prefix feeds both a deep low-resolution global-feature branch and a high-resolution detail skip, merged by a feature-fusion module — eliminating the duplicate early downsampling that two-branch segmenters pay.
Appears in 1 narrative
Lineage
Papers in the Atlas registry only · one dot per paperBuilt upon by · 0
Builds on · 6
2014Very Deep Convolutional Networks for Large-Scale Image RecognitionSimonyan, Zisserman2015Fully Convolutional Networks for Semantic SegmentationLong, Shelhamer, Darrell2015U-Net: Convolutional Networks for Biomedical Image SegmentationRonneberger, Fischer, Brox2016Deep Residual Learning for Image RecognitionHe, Zhang et al.2018DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsChen, Papandreou et al.2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic SegmentationYu, Wang et al.Built upon by · 0