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

State-of-the-art multimodal semantic segmentation approaches combining LiDARand color data are usually designed on top of asymmetric information-sharingschemes and assume that both modalities are always available. Regrettably, thisstrong assumption may not hold in real-world scenarios, where sensors are proneto failure or can face adverse conditions (night-time, rain, fog, etc.) thatmake the acquired information unreliable. Moreover, these architectures tend tofail in continual learning scenarios. In this work, we re-frame the task ofmultimodal semantic segmentation by enforcing a tightly-coupled featurerepresentation and a symmetric information-sharing scheme, which allows ourapproach to work even when one of the input modalities is missing. This makesour model reliable even in safety-critical settings, as is the case ofautonomous driving. We evaluate our approach on the SemanticKITTI dataset,comparing it with our closest competitor. We also introduce an ad-hoc continuallearning scheme and show results in a class-incremental continual learningscenario that prove the effectiveness of the approach also in this setting.

Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network