Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data. We propose two methods for selecting the most relevant data with weak supervision. The first method is designed for finding visually similar images without the need of labels and is based on modeling image representations with a Gaussian Mixture Model (GMM). As a byproduct of GMM modeling, we present useful insights on characterizing the data generating distribution. The second method aims at finding images with high object diversity and requires only the bounding box labels. Both methods are developed in the context of automated driving and experimentation is conducted on Cityscapes and Open Images datasets. We demonstrate performance gains by reducing the amount of employed weakly labeled images up to 100 times for Open Images and up to 20 times for Cityscapes.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Data Selection for training Semantic Segmentation CNNs with cross-dataset weak supervision


    Beteiligte:


    Erscheinungsdatum :

    01.10.2019


    Format / Umfang :

    2125757 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    On Boosting Semantic Street Scene Segmentation with Weak Supervision

    Meletis, Panagiotis / Dubbelman, Gijs | IEEE | 2019


    Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation

    Niemeijer, Joshua / Schäfer, P. Jörg | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021

    Freier Zugriff


    Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection

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