Varying and combining loss functions in deep visual saliency prediction models produces significant performance gains on fixed architectures that hold across datasets and networks.
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
-
Deep Saliency Models : The Quest For The Loss Function
Varying and combining loss functions in deep visual saliency prediction models produces significant performance gains on fixed architectures that hold across datasets and networks.