360SFUDA++ Towards Source-Free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes

360SFUDA++ : Towards Source-Free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes

In this paper, we address the challenging source-free unsupervised domain adaptation (SFUDA) for pinhole-to-panoramic semantic segmentation, given only a pinhole image pre-trained model (i.e., source) and unlabeled panoramic images (i.e., target). Tackling this problem is non-trivial due to three cr...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 04. Nov.
1. Verfasser: Zheng, Xu (VerfasserIn)
Weitere Verfasser: Zhou, Peng Yuan, Vasilakos, Athanasios V, Wang, Lin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
Online verfügbar Volltext