Observability-constrained test-time prompt tuning for LiDAR semantic segmentation reweights spatial supervision using per-location reliability estimates from beam terminations and neighborhood support, with prompt adapters and temporal prototype alignment.
Prompt tuning for generative multimodal pretrained models.arXiv preprint arXiv:2208.02532, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation
Observability-constrained test-time prompt tuning for LiDAR semantic segmentation reweights spatial supervision using per-location reliability estimates from beam terminations and neighborhood support, with prompt adapters and temporal prototype alignment.