KDMOS distills knowledge from the MambaMOS teacher into a lightweight BEV student, using class-decoupled and label-weighted distillation, reaching 78.8% IoU on SemanticKITTI-MOS.
Moving object segmentation in 3d lidar data: A learning-based approach exploiting sequential data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
KDMOS:Knowledge Distillation for Motion Segmentation
KDMOS distills knowledge from the MambaMOS teacher into a lightweight BEV student, using class-decoupled and label-weighted distillation, reaching 78.8% IoU on SemanticKITTI-MOS.