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

Convolutional neural networks (CNNs) have become the most successful approachin many vision-related domains. However, they are limited to domains where datais abundant. Recent works have looked at multi-task learning (MTL) to mitigatedata scarcity by leveraging domain-specific information from related tasks. Inthis paper, we present a novel soft-parameter sharing mechanism for CNNs in aMTL setting, which we refer to as Deep Collaboration. We propose taking intoaccount the notion that task relevance depends on depth by using lateraltransformation blocs with skip connections. This allows extractingtask-specific features at various depth without sacrificing features relevantto all tasks. We show that CNNs connected with our Deep Collaboration obtainbetter accuracy on facial landmark detection with related tasks. We finallyverify that our approach effectively allows knowledge sharing by showingdepth-specific influence of tasks that we know are related.

Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection