Semantic attributes as supervision for feature selection enable models trained on seen classes to select discriminative features for unseen classes, outperforming label-based and unsupervised baselines on SUN, aPY and CIFAR10.
Bidirectional feature selection with global and local structure preservation for small size samples
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
-
Zero-Shot Feature Selection via Transferring Supervised Knowledge
Semantic attributes as supervision for feature selection enable models trained on seen classes to select discriminative features for unseen classes, outperforming label-based and unsupervised baselines on SUN, aPY and CIFAR10.