Open-Set Domain Adaptation

Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation

In this paper, we addressed the open-set domain adaptation (OSDA) problem. We propose three new approaches to improve OSDA methods by using unknown samples to tighten the classification boundaries of the model.

Lucas Fernando Alvarenga e Silva, Nicu Sebe, Jurandy Almeida

Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation