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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Image clustering is a very useful technique that is widely applied to variousareas, including remote sensing. Recently, visual representations byself-supervised learning have greatly improved the performance of imageclustering. To further improve the well-trained clustering models, this paperproposes a novel method by first ranking samples within each cluster based onthe confidence in their belonging to the current cluster and then using theranking to formulate a weighted cross-entropy loss to train the model. Forranking the samples, we developed a method for computing the likelihood ofsamples belonging to the current clusters based on whether they are situated indensely populated neighborhoods, while for training the model, we give astrategy for weighting the ranked samples. We present extensive experimentalresults that demonstrate that the new technique can be used to improve theState-of-the-Art image clustering models, achieving accuracy performance gainsranging from $2.1\%$ to $15.9\%$. Performing our method on a variety ofdatasets from remote sensing, we show that our method can be effectivelyapplied to remote--sensing images.

Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images