Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is particularly noticeable along class boundaries, invalidating one of the main goals of semantic segmentation that consists in obtaining sharp segmentation masks.In this work, we specifically address this core problem in the context of Unsupervised Domain Adaptation and present a novel low-level adaptation strategy that allows us to obtain sharp predictions. Moreover, inspired by recent self-training techniques, we introduce an effective data augmentation that alleviates the noise typically present at semantic boundaries when employing pseudo-labels for self-training. Our contributions can be easily integrated into other popular adaptation frameworks, and extensive experiments show that they effectively improve performance along class boundaries.

Shallow Features Guide Unsupervised Domain Adaptation for Semantic Segmentation at Class Boundaries

Adriano Cardace;Pierluigi Zama Ramirez;Samuele Salti;Luigi Di Stefano
2022

Abstract

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is particularly noticeable along class boundaries, invalidating one of the main goals of semantic segmentation that consists in obtaining sharp segmentation masks.In this work, we specifically address this core problem in the context of Unsupervised Domain Adaptation and present a novel low-level adaptation strategy that allows us to obtain sharp predictions. Moreover, inspired by recent self-training techniques, we introduce an effective data augmentation that alleviates the noise typically present at semantic boundaries when employing pseudo-labels for self-training. Our contributions can be easily integrated into other popular adaptation frameworks, and extensive experiments show that they effectively improve performance along class boundaries.
2022
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
2010
2020
Adriano Cardace; Pierluigi Zama Ramirez; Samuele Salti; Luigi Di Stefano
File in questo prodotto:
File Dimensione Formato  
main.pdf

accesso aperto

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 782.31 kB
Formato Adobe PDF
782.31 kB 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/11585/864985
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 2
social impact