Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/134825
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Evaluating merging strategies for sampling-based uncertainty techniques in object detection |
Author: | Miller, D. Dayoub, F. Milford, M. Sunderhauf, N. |
Citation: | IEEE International Conference on Robotics and Automation, 2019 / Howard, A., Althoefer, K., Arai, F., Arrichiello, F., Caputo, B., Castellanos, J., Hauser, K., Isler, V., Kim, J., Liu, H., Oh, P., Santos, V., Scaramuzza, D., Ude, A., Voyles, R., Yamane, K., Okamura, A. (ed./s), vol.2019-May, pp.2348-2354 |
Publisher: | IEEE |
Publisher Place: | online |
Issue Date: | 2019 |
Series/Report no.: | IEEE International Conference on Robotics and Automation ICRA |
ISBN: | 9781538660263 |
ISSN: | 1050-4729 2577-087X |
Conference Name: | International Conference on Robotics and Automation (ICRA) (20 May 2019 - 24 May 2019 : Montreal, Canada) |
Editor: | Howard, A. Althoefer, K. Arai, F. Arrichiello, F. Caputo, B. Castellanos, J. Hauser, K. Isler, V. Kim, J. Liu, H. Oh, P. Santos, V. Scaramuzza, D. Ude, A. Voyles, R. Yamane, K. Okamura, A. |
Statement of Responsibility: | Dimity Miller, Feras Dayoub, Michael Milford, and Niko Sunderhauf |
Abstract: | There has been a recent emergence of samplingbased techniques for estimating epistemic uncertainty in deep neural networks. While these methods can be applied to classification or semantic segmentation tasks by simply averaging samples, this is not the case for object detection, where detection sample bounding boxes must be accurately associated and merged. A weak merging strategy can significantly degrade the performance of the detector and yield an unreliable uncertainty measure. This paper provides the first in-depth investigation of the effect of different association and merging strategies. We compare different combinations of three spatial and two semantic affinity measures with four clustering methods for MC Dropout with a Single Shot Multi-Box Detector. Our results show that the correct choice of affinity-clustering combination can greatly improve the effectiveness of the classification and spatial uncertainty estimation and the resulting object detection performance. We base our evaluation on a new mix of datasets that emulate near open-set conditions (semantically similar unknown classes), distant open-set conditions (semantically dissimilar unknown classes) and the common closed-set conditions (only known classes). |
Keywords: | Uncertainty; Object detection; Detectors; Clustering methods; Semantics; Measurement uncertainty; Robots |
Rights: | ©2019 IEEE |
DOI: | 10.1109/ICRA.2019.8793821 |
Grant ID: | http://purl.org/au-research/grants/arc/CE140100016 http://purl.org/au-research/grants/arc/FT140101229 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/8780387/proceeding |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.