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 this work, we have worked towards two major goals. Firstly, we haveinvestigated the importance of Batch Normalisation (BN) layers in anon-contrastive representation learning framework called Bootstrap Your OwnLatent (BYOL). We conducted several experiments to conclude that BN layers arenot necessary for representation learning in BYOL. Moreover, BYOL only learnsfrom the positive pairs of images but ignores other semantically similar imagesin the same input batch. For the second goal, we have introduced two new lossfunctions to determine the semantically similar pairs in the same input batchof images and reduce the distance between their representations. These lossfunctions are Cross-Cosine Similarity Loss (CCSL) and Cross-Sigmoid SimilarityLoss (CSSL). Using the proposed loss functions, we are able to surpass theperformance of Vanilla BYOL (71.04%) by training the BYOL framework using CCSLloss (76.87%) on the STL10 dataset. BYOL trained using CSSL loss performscomparably with Vanilla BYOL.

Self-Labeling Refinement for Robust Representation Learning with Bootstrap Your Own Latent