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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:


    Publication date :

    2023-09-24


    Size :

    3068760 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    LATENT OUTLIER EXPOSURE ZUR ANOMALIEERKENNUNG

    RUDOLPH MAJA / QIU CHEN | European Patent Office | 2023

    Free access

    AUTOMATIC CROSS-SENSOR CALIBRATION USING OBJECT DETECTIONS

    DIJKMAN DANIEL HENDRICUS FRANCISCUS / BEN YAHIA HAITAM / SUBRAMANIAN SUNDAR et al. | European Patent Office | 2023

    Free access

    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. | European Patent Office | 2019

    Free access

    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