CoinNet, a convolutional network combining compact bilinear pooling, residual blocks, and attention, achieves 98.5% top-1 accuracy on the new 100-class RRCD-Main dataset of Roman Republican coin reverses.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Ancient Roman Republican Coin Classification via Feature Fusion and Attention
CoinNet, a convolutional network combining compact bilinear pooling, residual blocks, and attention, achieves 98.5% top-1 accuracy on the new 100-class RRCD-Main dataset of Roman Republican coin reverses.