Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss. (arXiv:2208.08815v1 [cs.CV])

Domain adaptation is of huge interest as labeling is an expensive and
error-prone task, especially when labels are needed on pixel-level like in
semantic segmentation. Therefore, one would like to be able to train neural
networks on synthetic domains, where data is abundant and labels are precise.
However, these models often perform poorly on out-of-domain images. To mitigate
the shift in the input, image-to-image approaches can be used. Nevertheless,
standard image-to-image approaches that bridge the domain of deployment with
the …

arxiv cv cyclegan domain adaptation loss semi-supervised