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

Successive proposals of several self-supervised training schemes continue toemerge, taking one step closer to developing a universal foundation model. Inthis process, the unsupervised downstream tasks are recognized as one of theevaluation methods to validate the quality of visual features learned with aself-supervised training scheme. However, unsupervised dense semanticsegmentation has not been explored as a downstream task, which can utilize andevaluate the quality of semantic information introduced in patch-level featurerepresentations during self-supervised training of a vision transformer.Therefore, this paper proposes a novel data-driven approach for unsupervisedsemantic segmentation (DatUS^2) as a downstream task. DatUS^2 generatessemantically consistent and dense pseudo annotate segmentation masks for theunlabeled image dataset without using any visual-prior or synchronized data. Wecompare these pseudo-annotated segmentation masks with ground truth masks forevaluating recent self-supervised training schemes to learn shared semanticproperties at the patch level and discriminative semantic properties at thesegment level. Finally, we evaluate existing state-of-the-art self-supervisedtraining schemes with our proposed downstream task, i.e., DatUS^2. Also, thebest version of DatUS^2 outperforms the existing state-of-the-art method forthe unsupervised dense semantic segmentation task with 15.02% MiOU and 21.47%Pixel accuracy on the SUIM dataset. It also achieves a competitive level ofaccuracy for a large-scale and complex dataset, i.e., the COCO dataset.

DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer