English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Learning to hash is an efficient paradigm for exact and approximate nearestneighbor search from massive databases. Binary hash codes are typicallyextracted from an image by rounding output features from a CNN, which istrained on a supervised binary similar/ dissimilar task. Drawbacks of thisapproach are: (i) resulting codes do not necessarily capture semanticsimilarity of the input data (ii) rounding results in information loss,manifesting as decreased retrieval performance and (iii) Using only class-wisesimilarity as a target can lead to trivial solutions, simply encodingclassifier outputs rather than learning more intricate relations, which is notdetected by most performance metrics. We overcome (i) via a novel loss functionencouraging the relative hash code distances of learned features to match thosederived from their targets. We address (ii) via a differentiable estimate ofthe KL divergence between network outputs and a binary target distribution,resulting in minimal information loss when the features are rounded to binary.Finally, we resolve (iii) by focusing on a hierarchical precision metric.Efficiency of the methods is demonstrated with semantic image retrieval on theCIFAR-100, ImageNet and Conceptual Captions datasets, using similaritiesinferred from the WordNet label hierarchy or sentence embeddings.

Learning to hash with semantic similarity metrics and empirical KL divergence