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

Many researchers believe that ConvNets perform well on small or moderatelysized datasets, but are not competitive with Vision Transformers when givenaccess to datasets on the web-scale. We challenge this belief by evaluating aperformant ConvNet architecture pre-trained on JFT-4B, a large labelled datasetof images often used for training foundation models. We consider pre-trainingcompute budgets between 0.4k and 110k TPU-v4 core compute hours, and train aseries of networks of increasing depth and width from the NFNet model family.We observe a log-log scaling law between held out loss and compute budget.After fine-tuning on ImageNet, NFNets match the reported performance of VisionTransformers with comparable compute budgets. Our strongest fine-tuned modelachieves a Top-1 accuracy of 90.4%.

ConvNets Match Vision Transformers at Scale