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

Service robots are integrating more and more into our daily lives to help uswith various tasks. In such environments, robots frequently face new objectswhile working in the environment and need to learn them in an open-endedfashion. Furthermore, such robots must be able to recognize a wide range ofobject categories. In this paper, we present a lifelong ensemble learningapproach based on multiple representations to address the few-shot objectrecognition problem. In particular, we form ensemble methods based on deeprepresentations and handcrafted 3D shape descriptors. To facilitate lifelonglearning, each approach is equipped with a memory unit for storing andretrieving object information instantly. The proposed model is suitable foropen-ended learning scenarios where the number of 3D object categories is notfixed and can grow over time. We have performed extensive sets of experimentsto assess the performance of the proposed approach in offline, and open-endedscenarios. For the evaluation purpose, in addition to real object datasets, wegenerate a large synthetic household objects dataset consisting of 27000 viewsof 90 objects. Experimental results demonstrate the effectiveness of theproposed method on online few-shot 3D object recognition tasks, as well as itssuperior performance over the state-of-the-art open-ended learning approaches.Furthermore, our results show that while ensemble learning is modestlybeneficial in offline settings, it is significantly beneficial in lifelongfew-shot learning situations. Additionally, we demonstrated the effectivenessof our approach in both simulated and real-robot settings, where the robotrapidly learned new categories from limited examples.

Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition