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

Recent advance of large scale similarity search involves using deeply learnedrepresentations to improve the search accuracy and use vector quantizationmethods to increase the search speed. However, how to learn deeprepresentations that strongly preserve similarities between data pairs and canbe accurately quantized via vector quantization remains a challenging task.Existing methods simply leverage quantization loss and similarity loss, whichresult in unexpectedly biased back-propagating gradients and affect the searchperformances. To this end, we propose a novel gradient snapping layer (GSL) todirectly regularize the back-propagating gradient towards a neighboringcodeword, the generated gradients are un-biased for reducing similarity lossand also propel the learned representations to be accurately quantized. Jointdeep representation and vector quantization learning can be easily performed byalternatively optimize the quantization codebook and the deep neural network.The proposed framework is compatible with various existing vector quantizationapproaches. Experimental results demonstrate that the proposed framework iseffective, flexible and outperforms the state-of-the-art large scale similaritysearch methods.

Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search