A deep hashing method that replaces one-hot class labels with semantic hierarchy distances and adds an empirical KL loss, improving binary-code hierarchical retrieval on CIFAR-100 and ImageNet.
HashNet: Deep Learning to Hash by Continuation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SHREWD: Semantic Hierarchy-based Relational Embeddings for Weakly-supervised Deep Hashing
A deep hashing method that replaces one-hot class labels with semantic hierarchy distances and adds an empirical KL loss, improving binary-code hierarchical retrieval on CIFAR-100 and ImageNet.