3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and environments. Researchers working on UDA problems in the image domain have shown that sample mixing can mitigate domain shift. We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing. CoSMix consists of a two-branch symmetric network that can process labelled synthetic data (source) and real-world unlabelled point clouds (target) concurrently. Each branch operates on one domain by mixing selected pieces of data from the other one, and by using the semantic information derived from source labels and target pseudo-labels. We evaluate CoSMix on two large-scale datasets, showing that it outperforms state-of-the-art methods by a large margin (Our code is available at https://github.com/saltoricristiano/cosmix-uda ).

CoSMix. Compositional semantic mix for domain adaptation in 3D LiDAR segmentation / Saltori, Cristiano; Galasso, Fabio; Fiameni, Giuseppe; Sebe, Nicu; Ricci, Elisa; Fabiopoiesi,. - 13693 LNCS:(2022), pp. 586-602. (Intervento presentato al convegno 17th European Conference on Computer Vision, ECCV 2022 tenutosi a Tel Aviv; Israel) [10.1007/978-3-031-19827-4_34].

CoSMix. Compositional semantic mix for domain adaptation in 3D LiDAR segmentation

Fabio Galasso
Secondo
;
Elisa Ricci;
2022

Abstract

3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and environments. Researchers working on UDA problems in the image domain have shown that sample mixing can mitigate domain shift. We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing. CoSMix consists of a two-branch symmetric network that can process labelled synthetic data (source) and real-world unlabelled point clouds (target) concurrently. Each branch operates on one domain by mixing selected pieces of data from the other one, and by using the semantic information derived from source labels and target pseudo-labels. We evaluate CoSMix on two large-scale datasets, showing that it outperforms state-of-the-art methods by a large margin (Our code is available at https://github.com/saltoricristiano/cosmix-uda ).
2022
17th European Conference on Computer Vision, ECCV 2022
computer vision; machine learning; 3D; LiDAR; segmentation; domain adaptation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
CoSMix. Compositional semantic mix for domain adaptation in 3D LiDAR segmentation / Saltori, Cristiano; Galasso, Fabio; Fiameni, Giuseppe; Sebe, Nicu; Ricci, Elisa; Fabiopoiesi,. - 13693 LNCS:(2022), pp. 586-602. (Intervento presentato al convegno 17th European Conference on Computer Vision, ECCV 2022 tenutosi a Tel Aviv; Israel) [10.1007/978-3-031-19827-4_34].
File allegati a questo prodotto
File Dimensione Formato  
Saltori_CoSMix_2022.pdf

accesso aperto

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.23 MB
Formato Adobe PDF
1.23 MB Adobe PDF

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/11573/1666767
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? 8
social impact