Transfer Beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation

• Published in: IEEE transactions on intelligent transportation systems 2022-07, Vol.23 (7), p.9478-9491
• Main Authors: Zhang, Jiaming, Ma, Chaoxiang, Yang, Kailun, Roitberg, Alina, Peng, Kunyu, Stiefelhagen, Rainer
• Format: Article
• Language: English
• Subjects: Adaptation; Adaptation models; Cameras; domain adaptation; Domains; Image segmentation; intelligent vehicles; panoramic segmentation; Pinhole cameras; scene parsing; Semantic segmentation; Semantics; Task analysis; Training; Training data
• ISSN: 1524-9050; 1558-0016
• DOI: 10.1109/TITS.2021.3123070

Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360° sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic images. We look at this problem from the perspective of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images. To achieve this, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation and collect DensePass - a novel densely annotated dataset for panoramic segmentation under cross-domain conditions, specifically built to study the Pinhole \rightarrow PANORAMIC domain shift and accompanied with pinhole camera training examples obtained from Cityscapes. DensePass covers both, labelled- and unlabelled 360° images, with the labelled data comprising 19 classes which explicitly fit the categories available in the source ( i.e. pinhole) domain. Since data-driven models are especially susceptible to changes in data distribution, we introduce P2PDA - a generic framework for Pinhole \rightarrow Panoramic semantic segmentation which addresses the challenge of domain divergence with different variants of attention-augmented domain adaptation modules, enabling the transfer in output-, feature-, and feature confidence spaces. P2PDA intertwines uncertainty-aware adaptation using confidence values regulated on-the-fly through attention heads with discrepant predictions. Our framework facilitates context exchange when learning domain correspondences and dramatically improves the adaptation performance of accuracy- and efficiency-focused models. Comprehensive experiments verify that our framework clearly surpasses unsupervised domain adaptation- and specialized panoramic segmentation approaches as well as state-of-the-art semantic segmentation methods.