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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Unsupervised Deep Distance Metric Learning (UDML) aims to learn samplesimilarities in the embedding space from an unlabeled dataset. Traditional UDMLmethods usually use the triplet loss or pairwise loss which requires the miningof positive and negative samples w.r.t. anchor data points. This is, however,challenging in an unsupervised setting as the label information is notavailable. In this paper, we propose a new UDML method that overcomes thatchallenge. In particular, we propose to use a deep clustering loss to learncentroids, i.e., pseudo labels, that represent semantic classes. Duringlearning, these centroids are also used to reconstruct the input samples. Ithence ensures the representativeness of centroids - each centroid representsvisually similar samples. Therefore, the centroids give information aboutpositive (visually similar) and negative (visually dissimilar) samples. Basedon pseudo labels, we propose a novel unsupervised metric loss which enforcesthe positive concentration and negative separation of samples in the embeddingspace. Experimental results on benchmarking datasets show that the proposedapproach outperforms other UDML methods.

Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding