A graph-based generator that models batch-wide correlations creates adaptive hard negatives and improves deep metric learning image retrieval on four benchmarks.
International Journal of Computer Vision 132, 6091–6106 (2024)
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
-
Globally Correlation-Aware Hard Negative Generation
A graph-based generator that models batch-wide correlations creates adaptive hard negatives and improves deep metric learning image retrieval on four benchmarks.