The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains.
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.
However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CNN features hold a more tractable mapping with domain discrimination.
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation.
Ranked #1 on Domain Generalization on GTA5-to-Cityscapes
Autonomous robots are developed to be robust enough to work beside humans and to carry out jobs efficiently.
We show, across the tested tasks, significant performance gains even with a fraction of the data used in distillation, without compromising on the metric.