Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

Open-Set Domain Adaptation (OSDA) assumes that a target domain contains unknown classes, which are not discovered in a source domain. Existing domain adversarial learning methods are not suitable for OSDA because distribution matching with \(\textit{unknown}\) classes leads to negative transfer. Pre...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-10
Hauptverfasser:	Jang, JoonHo, Byeonghu Na, Shin, DongHyeok, Ji, Mingi, Song, Kyungwoo, Il-Chul Moon
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Alignment Domains Learning Matching
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!