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

3D object recognition has successfully become an appealing research topic inthe real-world. However, most existing recognition models unreasonably assumethat the categories of 3D objects cannot change over time in the real-world.This unrealistic assumption may result in significant performance degradationfor them to learn new classes of 3D objects consecutively, due to thecatastrophic forgetting on old learned classes. Moreover, they cannot explorewhich 3D geometric characteristics are essential to alleviate the catastrophicforgetting on old classes of 3D objects. To tackle the above challenges, wedevelop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net),which could recognize new classes of 3D objects continuously via overcoming thecatastrophic forgetting on old classes. Specifically, a category-guidedgeometric reasoning is proposed to reason local geometric structures withdistinctive 3D characteristics of each class by leveraging intrinsic categoryinformation. We then propose a novel critic-induced geometric attentionmechanism to distinguish which 3D geometric characteristics within each classare beneficial to overcome the catastrophic forgetting on old classes of 3Dobjects, while preventing the negative influence of useless 3D characteristics.In addition, a dual adaptive fairness compensations strategy is designed toovercome the forgetting brought by class imbalance, by compensating biasedweights and predictions of the classifier. Comparison experiments verify thestate-of-the-art performance of the proposed InOR-Net model on several publicpoint cloud datasets.

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation