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

In recent years, self-supervised learning has been studied to deal with thelimitation of available labeled-dataset. Among the major components ofself-supervised learning, the data augmentation pipeline is one key factor inenhancing the resulting performance. However, most researchers manuallydesigned the augmentation pipeline, and the limited collections oftransformation may cause the lack of robustness of the learned featurerepresentation. In this work, we proposed Multi-Augmentations forSelf-Supervised Representation Learning (MA-SSRL), which fully searched forvarious augmentation policies to build the entire pipeline to improve therobustness of the learned feature representation. MA-SSRL successfully learnsthe invariant feature representation and presents an efficient, effective, andadaptable data augmentation pipeline for self-supervised pre-training ondifferent distribution and domain datasets. MA-SSRL outperforms the previousstate-of-the-art methods on transfer and semi-supervised benchmarks whilerequiring fewer training epochs.

Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training