A semi-supervised teacher-student detector that applies a memory-aware regularizer and uncertainty weighting achieves near-full-supervised 3D detection accuracy with 22 to 25 percent of labels.
Revisiting modality imbalance in mul- timodal pedestrian detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure
A semi-supervised teacher-student detector that applies a memory-aware regularizer and uncertainty weighting achieves near-full-supervised 3D detection accuracy with 22 to 25 percent of labels.