Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F22%3A00359337" target="_blank" >RIV/68407700:21730/22:00359337 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-19839-7_28" target="_blank" >https://doi.org/10.1007/978-3-031-19839-7_28</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-19839-7_28" target="_blank" >10.1007/978-3-031-19839-7_28</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Popis výsledku v původním jazyce

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel method for cross-modal unsupervised learning of semantic image segmentation by leveraging synchronized LiDAR and image data. The key ingredient of our method is the use of an object proposal module that analyzes the LiDAR point cloud to obtain proposals for spatially consistent objects. Second, we show that these 3D object proposals can be aligned with the input images and reliably clustered into semantically meaningful pseudo-classes. Finally, we develop a cross-modal distillation approach that leverages image data partially annotated with the resulting pseudo-classes to train a transformer-based model for image semantic segmentation. We show the generalization capabilities of our method by testing on four different testing datasets (Cityscapes, Dark Zurich, Nighttime Driving and ACDC) without any finetuning, and demonstrate significant improvements compared to the current state of the art on this problem.

Název v anglickém jazyce

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Popis výsledku anglicky

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel method for cross-modal unsupervised learning of semantic image segmentation by leveraging synchronized LiDAR and image data. The key ingredient of our method is the use of an object proposal module that analyzes the LiDAR point cloud to obtain proposals for spatially consistent objects. Second, we show that these 3D object proposals can be aligned with the input images and reliably clustered into semantically meaningful pseudo-classes. Finally, we develop a cross-modal distillation approach that leverages image data partially annotated with the resulting pseudo-classes to train a transformer-based model for image semantic segmentation. We show the generalization capabilities of our method by testing on four different testing datasets (Cityscapes, Dark Zurich, Nighttime Driving and ACDC) without any finetuning, and demonstrate significant improvements compared to the current state of the art on this problem.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Vision – ECCV 2022, Part XXXVIII

ISBN

978-3-031-19838-0

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

18

Strana od-do

478-495

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Tel Aviv

Datum konání akce

23. 10. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000903760400028