A method for object detection obtains, from a set of RGB images lacking annotations, a set of regions that include potential objects, a bounding box, and an objectness score indicating a region prediction confidence. The method obtains, by a region scorer for each region in the set, a category from a fixed set of categories and a confidence for the category responsive to the objectness score. The method duplicates each region in the set to obtain a first and a second patch. The method encodes the patches to obtain an image vector. The method encodes a template sentence using the category to obtain a text vector for each category. The method compares the image vector to the text vector via a similarity function to obtain a similarity probability based on the confidence. The method defines a final set of pseudo labels based on the similarity probability being above a threshold.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    MINING UNLABELED IMAGES WITH VISION AND LANGUAGE MODELS FOR IMPROVING OBJECT DETECTION



    Erscheinungsdatum :

    2023-09-07


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    IPC:    G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G06V / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Finding Misdetections in Unlabeled Image Database: Toward Reliable Object Detection

    Koide, Satoshi / Kawano, Keisuke / Nakamura, Akihiro et al. | IEEE | 2021


    REPRESENTATION LEARNING FOR OBJECT DETECTION FROM UNLABELED POINT CLOUD SEQUENCES

    HUANG XIANGRU / WANG YUE / GUIZILINI VITOR et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Sensor Network Target Detection with Unlabeled Observarsations

    Sutton, achariah / Willet, Peter / Marano, Stefano | IEEE | 2020


    Learning the semantics of images by using unlabeled samples

    Fan, J. / Luo, H. / Gao, Y. | IEEE | 2005


    Unsupervised and simultaneous training of multiple object detectors from unlabeled surveillance video

    Celik, H. / Hanjalic, A. / Hendriks, E. A. | British Library Online Contents | 2009