Many weakly supervised semantic segmentation (WSSS) methods employ the class activation map (CAM) to generate the initial segmentation results. However, CAM often fails to distinguish the foreground from its co-occurred background (e.g., train and railroad), resulting in inaccurate activation from the background. Previous endeavors address this co-occurrence issue by introducing external supervision and human priors. In this paper, we present a False Positive Rectification (FPR) approach to tackle the co-occurrence problem by leveraging the false positives of CAM. Based on the observation that the CAM-activated regions of absent classes contain class-specific co-occurred background cues, we collect these false positives and utilize them to guide the training of CAM network by proposing a region-level contrast loss and a pixel-level rectification loss. Without introducing any external supervision and human priors, the proposed FPR effectively suppresses wrong activations from the background objects. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 demonstrate that FPR brings significant improvements for off-the-shelf methods and achieves state-of-the-art performance. Code is available at https://github.com/mt-cly/FPR.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    FPR: False Positive Rectification for Weakly Supervised Semantic Segmentation


    Beteiligte:
    Chen, Liyi (Autor:in) / Lei, Chenyang (Autor:in) / Li, Ruihuang (Autor:in) / Li, Shuai (Autor:in) / Zhang, Zhaoxiang (Autor:in) / Zhang, Lei (Autor:in)


    Erscheinungsdatum :

    01.10.2023


    Format / Umfang :

    2256650 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Weakly-Supervised Semantic Segmentation Network With Iterative dCRF

    Li, Yujie / Sun, Jiaxing / Li, Yun | IEEE | 2022


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

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


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

    VERNAZA PAUL / CHANDRAKER MANMOHAN | Europäisches Patentamt | 2019

    Freier Zugriff

    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