Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Syed, Qutub, Paulitsch, Michael, Hagn, Korbinian, Cihangir, Neslihan Kose, Scholl, Kay-Ulrich, Oboril, Fabian, Hinz, Gereon, Knoll, Alois
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.03188
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911905565638656
author Syed, Qutub
Paulitsch, Michael
Hagn, Korbinian
Cihangir, Neslihan Kose
Scholl, Kay-Ulrich
Oboril, Fabian
Hinz, Gereon
Knoll, Alois
author_facet Syed, Qutub
Paulitsch, Michael
Hagn, Korbinian
Cihangir, Neslihan Kose
Scholl, Kay-Ulrich
Oboril, Fabian
Hinz, Gereon
Knoll, Alois
contents We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situation Monitor utilizes the Diversity-based Budding Ensemble Architecture (DBEA) and increases the OOD performance by integrating a diversity loss into the training process on top of the budding ensemble architecture, detecting Far-OOD samples and minimizing false positives on Near-OOD samples. Moreover, utilizing the resulting DBEA increases the model's OOD performance and improves the calibration of confidence scores, particularly concerning the intersection over union of the detected objects. The DBEA model achieves these advancements with a 14% reduction in trainable parameters compared to the vanilla model. This signifies a substantial improvement in efficiency without compromising the model's ability to detect OOD instances and calibrate the confidence scores accurately.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03188
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection
Syed, Qutub
Paulitsch, Michael
Hagn, Korbinian
Cihangir, Neslihan Kose
Scholl, Kay-Ulrich
Oboril, Fabian
Hinz, Gereon
Knoll, Alois
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situation Monitor utilizes the Diversity-based Budding Ensemble Architecture (DBEA) and increases the OOD performance by integrating a diversity loss into the training process on top of the budding ensemble architecture, detecting Far-OOD samples and minimizing false positives on Near-OOD samples. Moreover, utilizing the resulting DBEA increases the model's OOD performance and improves the calibration of confidence scores, particularly concerning the intersection over union of the detected objects. The DBEA model achieves these advancements with a 14% reduction in trainable parameters compared to the vanilla model. This signifies a substantial improvement in efficiency without compromising the model's ability to detect OOD instances and calibrate the confidence scores accurately.
title Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.03188