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

We present a general methodology that learns to classify images withoutlabels by leveraging pretrained feature extractors. Our approach involvesself-distillation training of clustering heads based on the fact that nearestneighbours in the pretrained feature space are likely to share the same label.We propose a novel objective that learns associations between image features byintroducing a variant of pointwise mutual information together with instanceweighting. We demonstrate that the proposed objective is able to attenuate theeffect of false positive pairs while efficiently exploiting the structure inthe pretrained feature space. As a result, we improve the clustering accuracyover $k$-means on $17$ different pretrained models by $6.1$\% and $12.2$\% onImageNet and CIFAR100, respectively. Finally, using self-supervised visiontransformers, we achieve a clustering accuracy of $61.6$\% on ImageNet. Thecode is available at https://github.com/HHU-MMBS/TEMI-official-BMVC2023.

Exploring the Limits of Deep Image Clustering using Pretrained Models