In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data. The large domain shift between synthetic and real-world data, including the limited source environmental variations and the large distribution gap between synthetic and real-world data, significantly hinders the model performance on unseen real-world scenes. In this work, we propose the Style-HAllucinated Dual consistEncy learning (SHADE) framework to handle such domain shift. Specifically, SHADE is constructed based on two consistency constraints, Style Consistency (SC) and Retrospection Consistency (RC). SC enriches the source situations and encourages the model to learn consistent representation across style-diversified samples. RC leverages real-world knowledge to prevent the model from overfitting to synthetic data and thus largely keeps the representation consistent between the synthetic and real-world models. Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning. SHM selects basis styles from the source distribution, enabling the model to dynamically generate diverse and realistic samples during training. Experiments show that our SHADE yields significant improvement and outperforms state-of-the-art methods by 5.05% and 8.35% on the average mIoU of three real-world datasets on single- and multi-source settings, respectively.

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation / Zhao, Yuyang; Zhong, Zhun; Zhao, Na; Sebe, Nicu; Lee, Gim Hee. - 13688:(2022), pp. 535-552. (Intervento presentato al convegno European Conference on Computer Vision (ECCV) 17th European Conference tenutosi a Tel AvivI, Israel nel 23–27 October 2022) [10.1007/978-3-031-19815-1_31].

Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation

Zhong, Zhun;Sebe, Nicu;
2022-01-01

Abstract

In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data. The large domain shift between synthetic and real-world data, including the limited source environmental variations and the large distribution gap between synthetic and real-world data, significantly hinders the model performance on unseen real-world scenes. In this work, we propose the Style-HAllucinated Dual consistEncy learning (SHADE) framework to handle such domain shift. Specifically, SHADE is constructed based on two consistency constraints, Style Consistency (SC) and Retrospection Consistency (RC). SC enriches the source situations and encourages the model to learn consistent representation across style-diversified samples. RC leverages real-world knowledge to prevent the model from overfitting to synthetic data and thus largely keeps the representation consistent between the synthetic and real-world models. Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning. SHM selects basis styles from the source distribution, enabling the model to dynamically generate diverse and realistic samples during training. Experiments show that our SHADE yields significant improvement and outperforms state-of-the-art methods by 5.05% and 8.35% on the average mIoU of three real-world datasets on single- and multi-source settings, respectively.
2022
Computer Vision – ECCV 2022 17th European Conference
Cham
Springer
978-3-031-19814-4
978-3-031-19815-1
Zhao, Yuyang; Zhong, Zhun; Zhao, Na; Sebe, Nicu; Lee, Gim Hee
Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation / Zhao, Yuyang; Zhong, Zhun; Zhao, Na; Sebe, Nicu; Lee, Gim Hee. - 13688:(2022), pp. 535-552. (Intervento presentato al convegno European Conference on Computer Vision (ECCV) 17th European Conference tenutosi a Tel AvivI, Israel nel 23–27 October 2022) [10.1007/978-3-031-19815-1_31].
File in questo prodotto:
File Dimensione Formato  
136880530.pdf

Open Access dal 21/10/2023

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.43 MB
Formato Adobe PDF
1.43 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/11572/361314
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 6
social impact