A teacher-student pipeline trains a SECOND detector on clustering and heuristic pseudo-labels, but the claimed parity with human-annotated training is unsubstantiated.
Unsupervised lidar-based 3d object detection using infrastructure sensors, 2022
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
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
DINOSTAR: Deep Iterative Neural Object Detector Self-Supervised Training for Roadside LiDAR Applications
A teacher-student pipeline trains a SECOND detector on clustering and heuristic pseudo-labels, but the claimed parity with human-annotated training is unsubstantiated.