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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In recent years, representation learning approaches have disrupted manymultimedia computing tasks. Among those approaches, deep convolutional neuralnetworks (CNNs) have notably reached human level expertise on some constrainedimage classification tasks. Nonetheless, training CNNs from scratch for newtask or simply new data turns out to be complex and time-consuming. Recently,transfer learning has emerged as an effective methodology for adaptingpre-trained CNNs to new data and classes, by only retraining the lastclassification layer. This paper focuses on improving this process, in order tobetter transfer knowledge between CNN architectures for faster trainings in thecase of fine tuning for image classification. This is achieved by combining andtransfering supplementary weights, based on similarity considerations betweensource and target classes. The study includes a comparison between semantic andcontent-based similarities, and highlights increased initial performances andtraining speed, along with superior long term performances when limitedtraining samples are available.

Semantic and Visual Similarities for Efficient Knowledge Transfer in CNN Training