Benchmarking Sampling-based Probabilistic Object Detectors

Dimity Miller, Niko Sunderhauf, Haoyang Zhang, David Hall, Feras Dayoub; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 42-45


This paper provides the first benchmark for sampling- based probabilistic object detectors. A probabilistic object detector expresses uncertainty for all detections that reliably indicates object localisation and classification performance. We compare performance for two sampling-based uncertainty techniques, namely Monte Carlo Dropout and Deep Ensembles, when implemented into one-stage and two-stage object detectors, Single Shot MultiBox Detector and Faster R-CNN. Our results show that Deep Ensembles outperform MC Dropout for both types of detectors. We also introduce a new merging strategy for sampling-based techniques and one-stage object detectors. We show this novel merging strategy has competitive performance with previously established strategies, while only having one free parameter.

Related Material

author = {Miller, Dimity and Sunderhauf, Niko and Zhang, Haoyang and Hall, David and Dayoub, Feras},
title = {Benchmarking Sampling-based Probabilistic Object Detectors},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}