A soft-label entropy computed from logits averaged over training epochs is proposed as a data-pruning importance metric for ReID, with integrated label correction and outlier removal.
A survey of approaches and trends in person re-identification
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
-
Data Pruning Can Do More: A Comprehensive Data Pruning Approach for Object Re-identification
A soft-label entropy computed from logits averaged over training epochs is proposed as a data-pruning importance metric for ReID, with integrated label correction and outlier removal.