A point-to-region loss that propagates pseudo-label confidence to background pixels makes semi-supervised point-based crowd counting work and beats prior methods on ShTech, UCF-QNRF, and JHU++.
Rethinking spatial invariance of convolutional networks for object counting
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
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Point-to-Region Loss for Semi-Supervised Point-Based Crowd Counting
A point-to-region loss that propagates pseudo-label confidence to background pixels makes semi-supervised point-based crowd counting work and beats prior methods on ShTech, UCF-QNRF, and JHU++.