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

Negative sampling is a limiting factor w.r.t. the generalization ofmetric-learned neural networks. We show that uniform negative sampling provideslittle information about the class boundaries and thus propose three noveltechniques for efficient negative sampling: drawing negative samples from (1)the top-$k$ most semantically similar classes, (2) the top-$k$ mostsemantically similar samples and (3) interpolating between contrastive latentrepresentations to create pseudo negatives. Our experiments on CIFAR-10,CIFAR-100 and Tiny-ImageNet-200 show that our proposed \textit{SemanticallyConditioned Negative Sampling} and Latent Mixup lead to consistent performanceimprovements. In the standard supervised learning setting, on average weincrease test accuracy by 1.52\% percentage points on CIFAR-10 across variousnetwork architectures. In the knowledge distillation setting, (1) theperformance of student networks increase by 4.56\% percentage points onTiny-ImageNet-200 and 3.29\% on CIFAR-100 over student networks trained with noteacher and (2) 1.23\% and 1.72\% respectively over a \textit{hard-to-beat}baseline (Hinton et al., 2015).

Semantically-Conditioned Negative Samples for Efficient Contrastive Learning