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

The impressive performance of deep learning architectures is associated witha massive increase in model complexity. Millions of parameters need to betuned, with training and inference time scaling accordingly, together withenergy consumption. But is massive fine-tuning always necessary? In this paper,focusing on image classification, we consider a simple transfer learningapproach exploiting pre-trained convolutional features as input for afast-to-train kernel method. We refer to this approach as \textit{top-tuning}since only the kernel classifier is trained on the target dataset. In ourstudy, we perform more than 3000 training processes focusing on 32 small tomedium-sized target datasets, a typical situation where transfer learning isnecessary. We show that the top-tuning approach provides comparable accuracywith respect to fine-tuning, with a training time between one and two orders ofmagnitude smaller. These results suggest that top-tuning is an effectivealternative to fine-tuning in small/medium datasets, being especially usefulwhen training time efficiency and computational resources saving are crucial.

Top-Tuning: a study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods