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

During the last few years, continual learning (CL) strategies for imageclassification and segmentation have been widely investigated designinginnovative solutions to tackle catastrophic forgetting, like knowledgedistillation and self-inpainting. However, the application of continuallearning paradigms to point clouds is still unexplored and investigation isrequired, especially using architectures that capture the sparsity and unevendistribution of LiDAR data. The current paper analyzes the problem of classincremental learning applied to point cloud semantic segmentation, comparingapproaches and state-of-the-art architectures. To the best of our knowledge,this is the first example of class-incremental continual learning for LiDARpoint cloud semantic segmentation. Different CL strategies were adapted toLiDAR point clouds and tested, tackling both classic fine-tuning scenarios andthe Coarse-to-Fine learning paradigm. The framework has been evaluated throughtwo different architectures on SemanticKITTI, obtaining results in line withstate-of-the-art CL strategies and standard offline learning.

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data