ML Anthology

Probabilistic Object Detection via Deep Ensembles

Zongyao Lyu, Nolan Gutierrez, Aditya Rajguru, William J. Beksi
ECCVW 2020 pp. 67-75
doi:10.1007/978-3-030-65414-6_7 /eccvw/2020/lyu2020eccvw-probabilistic/

Abstract

Probabilistic object detection is the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detection. Measuring uncertainty is important in robotic applications where actions based on erroneous, but high confidence visual detections, can lead to catastrophic consequences. We introduce an approach that employs deep ensembles for estimating predictive uncertainty. The proposed framework achieved 4th place in the ECCV 2020 ACRV Robotic Vision Challenge on Probabilistic Object Detection.

PDF ECCVW Semantic Scholar

Cite

Text

Lyu et al. "Probabilistic Object Detection via Deep Ensembles." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-65414-6_7

Markdown

[Lyu et al. "Probabilistic Object Detection via Deep Ensembles." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/lyu2020eccvw-probabilistic/) doi:10.1007/978-3-030-65414-6_7

BibTeX

@inproceedings{lyu2020eccvw-probabilistic,
  title     = {{Probabilistic Object Detection via Deep Ensembles}},
  author    = {Lyu, Zongyao and Gutierrez, Nolan and Rajguru, Aditya and Beksi, William J.},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {67-75},
  doi       = {10.1007/978-3-030-65414-6_7},
  url       = {https://mlanthology.org/eccvw/2020/lyu2020eccvw-probabilistic/}
}