3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in unsupervised-domain-expansion-2
Use these libraries to find unsupervised-domain-expansion-2 models and implementations
No subtasks available.
This article proposes a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model’s performance on the source domain.
Co-Teaching (CT) is proposed, a method that instantiated with knowledge distillation based CT (kdCT) plus mixup based CT (miCT) that transfers knowledge from a leader-teacher network and an assistant-teacher network to a student network, so the cross-domain ambiguity will be better handled by the student.
Adding a benchmark result helps the community track progress.