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

Visual embeddings from Convolutional Neural Networks (CNN) trained on theImageNet dataset for the ILSVRC challenge have shown consistently goodperformance for transfer learning and are widely used in several tasks,including image recommendation. However, some important questions have not yetbeen answered in order to use these embeddings for a larger scope ofrecommendation domains: a) Do CNNs that perform better in ImageNet are alsobetter for transfer learning in content-based image recommendation?, b) Doesfine-tuning help to improve performance? and c) Which is the best way toperform the fine-tuning?  In this paper we compare several CNN models pre-trained with ImageNet toevaluate their transfer learning performance to an artwork image recommendationtask. Our results indicate that models with better performance in the ImageNetchallenge do not always imply better transfer learning for recommendation tasks(e.g. NASNet vs. ResNet). Our results also show that fine-tuning can be helpfuleven with a small dataset, but not every fine-tuning works. Our results caninform other researchers and practitioners on how to train their CNNs forbetter transfer learning towards image recommendation systems.

Do Better ImageNet Models Transfer Better... for Image Recommendation?