Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366999831> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4366999831 abstract "The ability to deploy robots that can operate safely in diverse environments is crucial for developing embodied intelligent agents. As a community, we have made tremendous progress in within-domain LiDAR semantic segmentation. However, do these methods generalize across domains? To answer this question, we design the first experimental setup for studying domain generalization (DG) for LiDAR semantic segmentation (DG-LSS). Our results confirm a significant gap between methods, evaluated in a cross-domain setting: for example, a model trained on the source dataset (SemanticKITTI) obtains $26.53$ mIoU on the target data, compared to $48.49$ mIoU obtained by the model trained on the target domain (nuScenes). To tackle this gap, we propose the first method specifically designed for DG-LSS, which obtains $34.88$ mIoU on the target domain, outperforming all baselines. Our method augments a sparse-convolutional encoder-decoder 3D segmentation network with an additional, dense 2D convolutional decoder that learns to classify a birds-eye view of the point cloud. This simple auxiliary task encourages the 3D network to learn features that are robust to sensor placement shifts and resolution, and are transferable across domains. With this work, we aim to inspire the community to develop and evaluate future models in such cross-domain conditions." @default.
- W4366999831 created "2023-04-27" @default.
- W4366999831 creator A5009902749 @default.
- W4366999831 creator A5065059558 @default.
- W4366999831 creator A5079316363 @default.
- W4366999831 creator A5090283032 @default.
- W4366999831 date "2023-04-23" @default.
- W4366999831 modified "2023-10-03" @default.
- W4366999831 title "Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation" @default.
- W4366999831 doi "https://doi.org/10.48550/arxiv.2304.11705" @default.
- W4366999831 hasPublicationYear "2023" @default.
- W4366999831 type Work @default.
- W4366999831 citedByCount "0" @default.
- W4366999831 crossrefType "posted-content" @default.
- W4366999831 hasAuthorship W4366999831A5009902749 @default.
- W4366999831 hasAuthorship W4366999831A5065059558 @default.
- W4366999831 hasAuthorship W4366999831A5079316363 @default.
- W4366999831 hasAuthorship W4366999831A5090283032 @default.
- W4366999831 hasBestOaLocation W43669998311 @default.
- W4366999831 hasConcept C111919701 @default.
- W4366999831 hasConcept C118505674 @default.
- W4366999831 hasConcept C119857082 @default.
- W4366999831 hasConcept C131979681 @default.
- W4366999831 hasConcept C134306372 @default.
- W4366999831 hasConcept C153180895 @default.
- W4366999831 hasConcept C154945302 @default.
- W4366999831 hasConcept C162324750 @default.
- W4366999831 hasConcept C177148314 @default.
- W4366999831 hasConcept C184337299 @default.
- W4366999831 hasConcept C187736073 @default.
- W4366999831 hasConcept C199360897 @default.
- W4366999831 hasConcept C205649164 @default.
- W4366999831 hasConcept C2780451532 @default.
- W4366999831 hasConcept C31972630 @default.
- W4366999831 hasConcept C33923547 @default.
- W4366999831 hasConcept C36503486 @default.
- W4366999831 hasConcept C41008148 @default.
- W4366999831 hasConcept C51399673 @default.
- W4366999831 hasConcept C62649853 @default.
- W4366999831 hasConcept C81363708 @default.
- W4366999831 hasConcept C89600930 @default.
- W4366999831 hasConcept C90509273 @default.
- W4366999831 hasConceptScore W4366999831C111919701 @default.
- W4366999831 hasConceptScore W4366999831C118505674 @default.
- W4366999831 hasConceptScore W4366999831C119857082 @default.
- W4366999831 hasConceptScore W4366999831C131979681 @default.
- W4366999831 hasConceptScore W4366999831C134306372 @default.
- W4366999831 hasConceptScore W4366999831C153180895 @default.
- W4366999831 hasConceptScore W4366999831C154945302 @default.
- W4366999831 hasConceptScore W4366999831C162324750 @default.
- W4366999831 hasConceptScore W4366999831C177148314 @default.
- W4366999831 hasConceptScore W4366999831C184337299 @default.
- W4366999831 hasConceptScore W4366999831C187736073 @default.
- W4366999831 hasConceptScore W4366999831C199360897 @default.
- W4366999831 hasConceptScore W4366999831C205649164 @default.
- W4366999831 hasConceptScore W4366999831C2780451532 @default.
- W4366999831 hasConceptScore W4366999831C31972630 @default.
- W4366999831 hasConceptScore W4366999831C33923547 @default.
- W4366999831 hasConceptScore W4366999831C36503486 @default.
- W4366999831 hasConceptScore W4366999831C41008148 @default.
- W4366999831 hasConceptScore W4366999831C51399673 @default.
- W4366999831 hasConceptScore W4366999831C62649853 @default.
- W4366999831 hasConceptScore W4366999831C81363708 @default.
- W4366999831 hasConceptScore W4366999831C89600930 @default.
- W4366999831 hasConceptScore W4366999831C90509273 @default.
- W4366999831 hasLocation W43669998311 @default.
- W4366999831 hasOpenAccess W4366999831 @default.
- W4366999831 hasPrimaryLocation W43669998311 @default.
- W4366999831 hasRelatedWork W1669643531 @default.
- W4366999831 hasRelatedWork W2005437358 @default.
- W4366999831 hasRelatedWork W2008656436 @default.
- W4366999831 hasRelatedWork W2517104666 @default.
- W4366999831 hasRelatedWork W2954561862 @default.
- W4366999831 hasRelatedWork W2976989770 @default.
- W4366999831 hasRelatedWork W3091155238 @default.
- W4366999831 hasRelatedWork W4226195147 @default.
- W4366999831 hasRelatedWork W4310264062 @default.
- W4366999831 hasRelatedWork W4312828305 @default.
- W4366999831 isParatext "false" @default.
- W4366999831 isRetracted "false" @default.
- W4366999831 workType "article" @default.