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

Data labeling in supervised learning is considered an expensive andinfeasible tool in some conditions. The self-supervised learning method isproposed to tackle the learning effectiveness with fewer labeled data, however,there is a lack of confidence in the size of labeled data needed to achieveadequate results. This study aims to draw a baseline on the proportion of thelabeled data that models can appreciate to yield competent accuracy whencompared to training with additional labels. The study implements thekaggle.com' cats-vs-dogs dataset, Mnist and Fashion-Mnist to investigate theself-supervised learning task by implementing random rotations augmentation onthe original datasets. To reveal the true effectiveness of the pretext processin self-supervised learning, the original dataset is divided into smallerbatches, and learning is repeated on each batch with and without the pretextpre-training. Results show that the pretext process in the self-supervisedlearning improves the accuracy around 15% in the downstream classification taskwhen compared to the plain supervised learning.

Investigating a Baseline Of Self Supervised Learning Towards Reducing Labeling Costs For Image Classification