This Autonomous driving methods driven by big data are becoming more and more perfect, but the cost of existing data labeling is too high, so how to reduce or even not label data has attracted more and more attention. Semantic segmentation networks supervised by image-level annotations are all trained using pseudo-labels. Most methods use image classification networks to generate class activation maps (CAMs) and start with CAMs to diffuse features to other parts of the target to obtain pseudo-labels. However, due to its weak supervision information, it is difficult for the existing methods to obtain better results. Therefore, we propose a weakly-supervised semantic segmentation network with iterative dCRF based on graph convolution. Specifically, we use ResNet to generate CAMs and node features and then use graph convolution for feature propagation and merge the low-level and high-level semantic information of the image. Then execute dCRF in an iterative manner, and finally obtain refined pseudo-labels. On the PASCAL VOC 2012 data set, our model achieves an mIoU of 63.5%, which is 0.3% higher than the graph convolutional network method.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Weakly-Supervised Semantic Segmentation Network With Iterative dCRF


    Beteiligte:
    Li, Yujie (Autor:in) / Sun, Jiaxing (Autor:in) / Li, Yun (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2022-12-01


    Format / Umfang :

    1588984 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar

    Kaul, Prannay / de Martini, Daniele / Gadd, Matthew et al. | IEEE | 2020



    Weakly supervised motion segmentation with particle matching

    Rahmati, Hodjat / Dragon, Ralf / Aamo, Ole Morten et al. | British Library Online Contents | 2015


    Weakly supervised motion segmentation with particle matching

    Rahmati, Hodjat / Dragon, Ralf / Aamo, Ole Morten et al. | British Library Online Contents | 2015


    System and method for learning random-walk label propagation for weakly-supervised semantic segmentation

    VERNAZA PAUL / CHANDRAKER MANMOHAN | Europäisches Patentamt | 2019

    Freier Zugriff