SPRED couples learnable identity prototypes with new-and-old model clustering to purify pseudo-labels, improving semi-supervised lifelong person re-identification at low label rates.
Exponential moving average normalization for self-supervised and semi- supervised learning
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
background 1representative citing papers
citing papers explorer
-
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
SPRED couples learnable identity prototypes with new-and-old model clustering to purify pseudo-labels, improving semi-supervised lifelong person re-identification at low label rates.