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.
Slim: Self-supervised lidar scene flow and motion seg- mentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.