SPGNet improves semantic segmentation by using a first stage's per-pixel predictions to re-weight features entering a second encoder-decoder stage.
Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SPGNet: Semantic Prediction Guidance for Scene Parsing
SPGNet improves semantic segmentation by using a first stage's per-pixel predictions to re-weight features entering a second encoder-decoder stage.