ST3D++ : Denoised Self-Training for Unsupervised Domain Adaptation on 3D Object Detection
In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as alleviating the negative impacts of noisy pseudo labels on mo...
Ausführliche Beschreibung
Bibliographische Detailangaben
Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 5 vom: 24. Mai, Seite 6354-6371
|
1. Verfasser: |
Yang, Jihan
(VerfasserIn) |
Weitere Verfasser: |
Shi, Shaoshuai,
Wang, Zhe,
Li, Hongsheng,
Qi, Xiaojuan |
Format: | Online-Aufsatz
|
Sprache: | English |
Veröffentlicht: |
2023
|
Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
Schlagworte: | Journal Article |