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

Image clustering is one of the most important computer vision applications,which has been extensively studied in literature. However, current clusteringmethods mostly suffer from lack of efficiency and scalability when dealing withlarge-scale and high-dimensional data. In this paper, we propose a newclustering model, called DEeP Embedded RegularIzed ClusTering (DEPICT), whichefficiently maps data into a discriminative embedding subspace and preciselypredicts cluster assignments. DEPICT generally consists of a multinomiallogistic regression function stacked on top of a multi-layer convolutionalautoencoder. We define a clustering objective function using relative entropy(KL divergence) minimization, regularized by a prior for the frequency ofcluster assignments. An alternating strategy is then derived to optimize theobjective by updating parameters and estimating cluster assignments.Furthermore, we employ the reconstruction loss functions in our autoencoder, asa data-dependent regularization term, to prevent the deep embedding functionfrom overfitting. In order to benefit from end-to-end optimization andeliminate the necessity for layer-wise pretraining, we introduce a jointlearning framework to minimize the unified clustering and reconstruction lossfunctions together and train all network layers simultaneously. Experimentalresults indicate the superiority and faster running time of DEPICT inreal-world clustering tasks, where no labeled data is available forhyper-parameter tuning.

Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization