Adding task-supervised auxiliary modules to shared layers during training improves hard-parameter-sharing multi-task learning on segmentation, depth, and surface normal prediction, with no inference-time overhead.
A bayesian/information theoretic model of learning to learn via multiple task sampling
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
-
Auxiliary Learning for Deep Multi-task Learning
Adding task-supervised auxiliary modules to shared layers during training improves hard-parameter-sharing multi-task learning on segmentation, depth, and surface normal prediction, with no inference-time overhead.