BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture

Qutub Syed (INTEL LABS),* Neslihan Kose Cihangir (Intel Deutschland GmbH), Rafael Rosales (Intel), Michael Paulitsch (Intel), Korbinian Hagn (Intel), Florian R Geissler (Intel), Yang Peng (Intel), Gereon Hinz (STTech GmbH), Alois C. Knoll (Robotics and Embedded Systems)
The 34th British Machine Vision Conference


This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial in vision-based tasks, particularly in autonomous systems. They should provide precise bounding box detections while also calibrating their predicted confidence scores, leading to higher-quality uncertainty estimates. However, current models may make erroneous decisions due to false positives receiving high scores or true positives being discarded due to low scores. BEA aims to address these issues. The proposed loss functions in BEA improve the confidence score calibration and lower the uncertainty error, which results in a better distinction of true and false positives and, eventually, higher accuracy of the object detection models. Both Base-YOLOv3 and SSD models were enhanced using the BEA method and its proposed loss functions. The BEA on Base-YOLOv3 trained on the KITTI dataset results in a 6\% and 3.7\% increase in mAP and AP50, respectively. Utilizing a well-balanced uncertainty estimation threshold to discard samples in real-time even leads to a 9.6\% higher AP50 than its base model. This is attributed to a 40\% increase in the area under the AP50-based retention curve used to measure the quality of calibration of confidence scores. Furthermore, BEA-YOLOV3 trained on KITTI provides superior out-of-distribution detection on Citypersons, BDD100K, and COCO datasets compared to the ensembles, base-YOLOv3, and Gaussian-YOLOv3 model.



author    = {Qutub Syed and Neslihan Kose Cihangir and Rafael Rosales and Michael Paulitsch and Korbinian Hagn and Florian R Geissler and Yang Peng and Gereon  Hinz and Alois C. Knoll},
title     = {BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year      = {2023},
url       = {}

Copyright © 2023 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection