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

Existing multi-stage clustering methods independently learn the salientfeatures from multiple views and then perform the clustering task.Particularly, multi-view clustering (MVC) has attracted a lot of attention inmulti-view or multi-modal scenarios. MVC aims at exploring common semantics andpseudo-labels from multiple views and clustering in a self-supervised manner.However, limited by noisy data and inadequate feature learning, such aclustering paradigm generates overconfident pseudo-labels that mis-guide themodel to produce inaccurate predictions. Therefore, it is desirable to have amethod that can correct this pseudo-label mistraction in multi-stage clusteringto avoid the bias accumulation. To alleviate the effect of overconfidentpseudo-labels and improve the generalization ability of the model, this paperproposes a novel multi-stage deep MVC framework where multi-viewself-distillation (DistilMVC) is introduced to distill dark knowledge of labeldistribution. Specifically, in the feature subspace at different hierarchies,we explore the common semantics of multiple views through contrastive learningand obtain pseudo-labels by maximizing the mutual information between views.Additionally, a teacher network is responsible for distilling pseudo-labelsinto dark knowledge, supervising the student network and improving itspredictive capabilities to enhance the robustness. Extensive experiments onreal-world multi-view datasets show that our method has better clusteringperformance than state-of-the-art methods.

Towards Generalized Multi-stage Clustering: Multi-view Self-distillation