Introduces semantic constraints to reduce bias-induced unwanted changes in diverse unpaired image-to-image translation while preserving desired transformations and output diversity.
Unbiased look at dataset bias, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Controlling biases and diversity in diverse image-to-image translation
Introduces semantic constraints to reduce bias-induced unwanted changes in diverse unpaired image-to-image translation while preserving desired transformations and output diversity.