Applying cycle-consistency GAN losses to steering-angle regression across synthetic and real driving domains yields a modest reported accuracy gain, but the method and the 'cyclic loss' are prior art from CyCADA.
Simultaneous deep transfer across domains and tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Cross Domain Adaptation using Adversarial networks with Cyclic loss
Applying cycle-consistency GAN losses to steering-angle regression across synthetic and real driving domains yields a modest reported accuracy gain, but the method and the 'cyclic loss' are prior art from CyCADA.