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

Nearest neighbor (NN) sampling provides more semantic variations thanpre-defined transformations for self-supervised learning (SSL) based imagerecognition problems. However, its performance is restricted by the quality ofthe support set, which holds positive samples for the contrastive loss. In thiswork, we show that the quality of the support set plays a crucial role in anynearest neighbor based method for SSL. We then provide a refined baseline(pNNCLR) to the nearest neighbor based SSL approach (NNCLR). To this end, weintroduce pseudo nearest neighbors (pNN) to control the quality of the supportset, wherein, rather than sampling the nearest neighbors, we sample in thevicinity of hard nearest neighbors by varying the magnitude of the resultantvector and employing a stochastic sampling strategy to improve the performance.Additionally, to stabilize the effects of uncertainty in NN-based learning, weemploy a smooth-weight-update approach for training the proposed network.Evaluation of the proposed method on multiple public image recognition andmedical image recognition datasets shows that it performs up to 8 percentbetter than the baseline nearest neighbor method, and is comparable to otherpreviously proposed SSL methods.

pNNCLR: Stochastic Pseudo Neighborhoods for Contrastive Learning based Unsupervised Representation Learning Problems