Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection

Syed Sha Qutub, Michael Paulitsch, Kay-Ulrich Scholl, Neslihan Kose Cihangir, Korbinian Hagn, Fabian Oboril, Gereon Hinz, Alois Knoll; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 3502-3511

We introduce Situation Monitor a novel zero-shot Outof-Distribution (OOD) detection approach for transformer based object detection models to enhance reliability in safetycritical 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.