AdaCo refurbishes noisy VFM-generated 3D pseudo labels using adaptive early-learning correction and robust losses, reaching 25.7% and 31.2% mIoU on SemanticKITTI and nuScenes without 3D annotations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AdaCo: Overcoming Visual Foundation Model Noise in 3D Semantic Segmentation via Adaptive Label Correction
AdaCo refurbishes noisy VFM-generated 3D pseudo labels using adaptive early-learning correction and robust losses, reaching 25.7% and 31.2% mIoU on SemanticKITTI and nuScenes without 3D annotations.