DyConfidMatch sets per-class pseudo-label thresholds and re-sampling weights from class-level confidence, improving semi-supervised 3D classification and detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning
DyConfidMatch sets per-class pseudo-label thresholds and re-sampling weights from class-level confidence, improving semi-supervised 3D classification and detection.