Semantic segmentation is a pixel-wise class identification problem, which is important for automatic driving support such as recognizing the driving area. However, segmentation accuracy significantly degrades in scenes that differ from the training domain. Therefore, it is necessary to prepare multiple models for each domain, which increases the memory cost. When training multiple datasets with a single-head model, it is also necessary to redefine a different object class for each dataset. We propose a semantic-segmentation method that involves using a multi-head model for supporting multiple domains. The proposed method also involves using a shared network for sharing all domains for training datasets. This makes it possible to train multiple datasets with different object classes in a single network. To train all datasets equally, we also introduce mix loss, which simultaneously back-propagates the loss of each dataset. From experiments evaluating the proposed method, we confirmed that the method achieves higher or equivalent recognition accuracy with fewer parameters than using a single-head model for each dataset when training datasets with the same class, training different datasets at the same time, and training datasets individually.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-Domain Semantic-Segmentation using Multi-Head Model


    Beteiligte:


    Erscheinungsdatum :

    2021-09-19


    Format / Umfang :

    1405856 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Confidence-and-Refinement Adaptation Model for Cross-Domain Semantic Segmentation

    Zhang, Xiaohong / Chen, Yi / Shen, Ziyi et al. | IEEE | 2022


    Augmentation-based Domain Generalization for Semantic Segmentation

    Schwonberg, Manuel / Bouazati, Fadoua El / Schmidt, Nico M. et al. | IEEE | 2023


    Efficient semantic image segmentation with multi-class ranking prior

    Pei, D. / Li, Z. / Ji, R. et al. | British Library Online Contents | 2014


    Conciliating syntactic and semantic constraints for multi-phase and multi-channel region segmentation

    Israel-Jost, V. / Darbon, J. r. / Angelini, E. D. et al. | British Library Online Contents | 2013


    MULTI-MODAL SEGMENTATION NETWORK FOR ENHANCED SEMANTIC LABELING IN MAPPING

    WIDJAJA SERGI ADIPRAJA / SHARMA DHANANJAI / LIONG VENICE ERIN B | Europäisches Patentamt | 2023

    Freier Zugriff