LiDAR semantic segmentation is receiving increased attention due to its deployment in autonomous driving applications. As LiDARs come often with other sensors such as RGB cameras, multi-modal approaches for this task have been developed, which however suffer from the domain shift problem as other deep learning approaches. To address this, we propose a novel Unsupervised Domain Adaptation (UDA) technique for multi-modal LiDAR segmentation. Unlike previous works in this field, we leverage depth completion as an auxiliary task to align features extracted from 2D images across domains, and as a powerful data augmentation for LiDARs. We validate our method on three popular multi-modal UDA benchmarks and we achieve better performances than other competitors.

Adriano Cardace, Andrea Conti, Pierluigi Zama Ramirez, Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano (2023). Boosting Multi-Modal Unsupervised Domain Adaptation for LiDAR Semantic Segmentation by Self-Supervised Depth Completion. IEEE ACCESS, 11, 85155-85164 [10.1109/ACCESS.2023.3304542].

Boosting Multi-Modal Unsupervised Domain Adaptation for LiDAR Semantic Segmentation by Self-Supervised Depth Completion

Adriano Cardace;Andrea Conti;Pierluigi Zama Ramirez;Riccardo Spezialetti;Samuele Salti;Luigi Di Stefano
2023

Abstract

LiDAR semantic segmentation is receiving increased attention due to its deployment in autonomous driving applications. As LiDARs come often with other sensors such as RGB cameras, multi-modal approaches for this task have been developed, which however suffer from the domain shift problem as other deep learning approaches. To address this, we propose a novel Unsupervised Domain Adaptation (UDA) technique for multi-modal LiDAR segmentation. Unlike previous works in this field, we leverage depth completion as an auxiliary task to align features extracted from 2D images across domains, and as a powerful data augmentation for LiDARs. We validate our method on three popular multi-modal UDA benchmarks and we achieve better performances than other competitors.
2023
Adriano Cardace, Andrea Conti, Pierluigi Zama Ramirez, Riccardo Spezialetti, Samuele Salti, Luigi Di Stefano (2023). Boosting Multi-Modal Unsupervised Domain Adaptation for LiDAR Semantic Segmentation by Self-Supervised Depth Completion. IEEE ACCESS, 11, 85155-85164 [10.1109/ACCESS.2023.3304542].
Adriano Cardace; Andrea Conti; Pierluigi Zama Ramirez; Riccardo Spezialetti; Samuele Salti; Luigi Di Stefano
File in questo prodotto:
File Dimensione Formato  
Boosting_Multi-Modal_Unsupervised_Domain_Adaptation_for_LiDAR_Semantic_Segmentation_by_Self-Supervised_Depth_Completion.pdf

accesso aperto

Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 2.41 MB
Formato Adobe PDF
2.41 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/955906
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact