The paper proposes an unsupervised domain alignment method using GANs with cycle consistency, adversarial, and SSIM losses to augment training data and reduce low-level dataset biases in computer vision.
Unsupervised domain adaptation for semantic segmentation with gans,
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
-
Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
The paper proposes an unsupervised domain alignment method using GANs with cycle consistency, adversarial, and SSIM losses to augment training data and reduce low-level dataset biases in computer vision.