LiDAR-based 3D object detectors have achieved unprecedented speed and accuracy in autonomous driving applications. However, similar to other neural networks, they are often biased toward high-confidence predictions or return detections where no real object is present. These types of detections can lead to a less reliable environment perception, severely affecting the functionality and safety of autonomous vehicles. We address this problem by proposing LS-VOS, a framework for identifying outliers in 3D object detections. Our approach builds on the idea of Virtual Outlier Synthesis (VOS), which incorporates outlier knowledge during training, enabling the model to learn more compact decision boundaries. In particular, we propose a new synthesis approach that relies on the latent space of an auto-encoder network to generate outlier features with a parametrizable degree of similarity to in-distribution features. In extensive experiments, we show that our approach improves the outlier detection capabilities of a state-of-the-art object detector while maintaining high 3D object detection performance.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    LS-VOS: Identifying Outliers in 3D Object Detections Using Latent Space Virtual Outlier Synthesis


    Beteiligte:
    Piroli, Aldi (Autor:in) / Dallabetta, Vinzenz (Autor:in) / Kopp, Johannes (Autor:in) / Walessa, Marc (Autor:in) / Meissner, Daniel (Autor:in) / Dietmayer, Klaus (Autor:in)


    Erscheinungsdatum :

    24.09.2023


    Format / Umfang :

    3068760 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LATENT OUTLIER EXPOSURE ZUR ANOMALIEERKENNUNG

    RUDOLPH MAJA / QIU CHEN | Europäisches Patentamt | 2023

    Freier Zugriff

    AUTOMATIC CROSS-SENSOR CALIBRATION USING OBJECT DETECTIONS

    DIJKMAN DANIEL HENDRICUS FRANCISCUS / BEN YAHIA HAITAM / SUBRAMANIAN SUNDAR et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Identifying Teen-Related Crash Hotspots and Outliers Using ArcGIS

    Mohammed, Hemin J. / Schrock, Steven D. | TIBKAT | 2020


    Accurate object proposals by tracking detections

    SCHULTER SAMUEL / CHOI WONGUN / SINGH BHARAT et al. | Europäisches Patentamt | 2019

    Freier Zugriff

    The Calibration and Characterization of IRAS Metric Resident Space Object Detections

    Lane, M. T. / Baldassini, J. / Gaposchkin, E. M. et al. | British Library Conference Proceedings | 1996