A network can improve its own lane detection by distilling attention maps from its deeper layers to its shallower layers during training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
A network can improve its own lane detection by distilling attention maps from its deeper layers to its shallower layers during training.