A Sample Selection Approach for Universal Domain Adaptation
This addresses domain adaptation for scenarios with partial class overlap, which is incremental as it builds on existing methods but offers specific improvements.
The paper tackles unsupervised domain adaptation where only some classes are shared between source and target domains, presenting a scoring scheme to identify shared-class samples and a loss for label diversity, resulting in outperforming state-of-the-art methods by a sizable margin on benchmarks.
We study the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of the shared classes. The score is used to select which samples in the target domain to pseudo-label during training. Another loss term encourages diversity of labels within each batch. Taken together, our method is shown to outperform, by a sizable margin, the current state of the art on the literature benchmarks.