arXiv Open Access 2020

A Sample Selection Approach for Universal Domain Adaptation

Omri Lifshitz Lior Wolf

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CV

Penulis (2)

Omri Lifshitz

Lior Wolf

Format Sitasi

APA MLA BibTeX

Lifshitz, O., Wolf, L. (2020). A Sample Selection Approach for Universal Domain Adaptation. https://arxiv.org/abs/2001.05071

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓