Year: 2019
Type: conference-paper
Abstract: This paper provides the first benchmark for sampling-based probabilistic object detectors. A probabilistic objectdetector expresses uncertainty for all detections that reli-ably indicates object localisation and classification perfor-mance. We compare performance for two sampling-baseduncertainty techniques, namely Monte Carlo Dropout andDeep Ensembles, when implemented into one-stage andtwo-stage object detectors, Single Shot MultiBox Detectorand Faster R-CNN. Our results show that Deep Ensemblesoutperform MC Dropout for both types of detectors. We alsointroduce a new merging strategy for sampling-based tech-niques and one-stage object detectors. We show this novelmerging strategy has competitive performance with previ-ously established strategies, while only having one free pa-rameter
Authors: Dimity Miller, Niko Suenderhauf, Haoyang Zhang, David Hall, Feras Dayoub
Institution: Queensland University of Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G252308265
OpenAlex ID: W2969779009