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

This paper introduces Multi-Level feature learning alongside the Embeddinglayer of Convolutional Autoencoder (CAE-MLE) as a novel approach in deepclustering. We use agglomerative clustering as the multi-level feature learningthat provides a hierarchical structure on the latent feature space. It is shownthat applying multi-level feature learning considerably improves the basic deepconvolutional embedding clustering (DCEC). CAE-MLE considers the clusteringloss of agglomerative clustering simultaneously alongside the learning latentfeature of CAE. In the following of the previous works in inverse featurelearning, we show that the representation of learning of error as a generalstrategy can be applied on different deep clustering approaches and it leads topromising results. We develop deep inverse feature learning (deep IFL) onCAE-MLE as a novel approach that leads to the state-of-the-art results amongthe same category methods. The experimental results show that the CAE-MLEimproves the results of the basic method, DCEC, around 7% -14% on twowell-known datasets of MNIST and USPS. Also, it is shown that the proposed deepIFL improves the primary results about 9%-17%. Therefore, both proposedapproaches of CAE-MLE and deep IFL based on CAE-MLE can lead to notableperformance improvement in comparison to the majority of existing techniques.The proposed approaches while are based on a basic convolutional autoencoderlead to outstanding results even in comparison to variational autoencoders orgenerative adversarial networks.

Multi-level Feature Learning on Embedding Layer of Convolutional Autoencoders and Deep Inverse Feature Learning for Image Clustering