Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is addressed by unsupervised domain adaptation (UDA) approaches trained either simultaneously on source and target domain datasets or even source-free only on target data in an offline fashion. In this work, we further expand a source-free UDA approach to a continual and therefore online-capable UDA on a single-image basis for semantic segmentation. Accordingly, our method only requires the pre-trained model from the supplier (trained in the source domain) and the current (unlabeled target domain) camera image. Our method Continual BatchNorm Adaptation (CBNA) modifies the source domain statistics in the batch normalization layers, using target domain images in an unsupervised fashion, which yields consistent performance improvements during inference. Thereby, in contrast to existing works, our approach can be applied to improve a DNN continuously on a single-image basis during deployment without access to source data, without algorithmic delay, and nearly without computational overhead. We show the consistent effectiveness of our method across a wide variety of source/target domain settings for semantic segmentation. Code is available at https://github.com/ifnspaml/CBNA


    Access

    Download


    Export, share and cite



    Title :

    Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation


    Contributors:

    Published in:

    Publication date :

    2022-11-01


    Size :

    3316196 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Effects of Architectures on Continual Semantic Segmentation

    Kalb, Tobias / Ahuja, Niket / Zhou, Jingxing et al. | IEEE | 2023


    Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

    Termohlen, Jan-Aike / Klingner, Marvin / Brettin, Leon J. et al. | IEEE | 2021


    Continual Learning for Class- and Domain-Incremental Semantic Segmentation

    Kalb, Tobias / Roschani, Masoud / Ruf, Miriam et al. | IEEE | 2021


    Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection

    Kalb, Tobias / Mauthe, Bjorn / Beyerer, Jurgen | IEEE | 2022


    Continual Cross-Dataset Adaptation in Road Surface Classification

    Cudrano, Paolo / Bellusci, Matteo / Macino, Giuseppe et al. | IEEE | 2023