LiPS is a streamlined panoptic segmentation architecture that matches heavier models in accuracy while delivering up to 4.5x higher throughput and 6.8x lower computation on standard benchmarks.
Pyramid vision transformer: A versatile back- bonefordensepredictionwithoutconvolutions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LiPS: Lightweight Panoptic Segmentation for Resource-Constrained Robotics
LiPS is a streamlined panoptic segmentation architecture that matches heavier models in accuracy while delivering up to 4.5x higher throughput and 6.8x lower computation on standard benchmarks.