Search
Abstract
In this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data augmentation. In this work, the robustness of existing data augmentation techniques is evaluated to propose a new simple augmentation scheme where during training, an image is combined with a patch of a stylized version of that image. Evaluation of pedestrian detection models robustness and uncertainty calibration under naturally occurring corruption and in realistic cross-dataset evaluation setting is conducted to show that our proposed solution improves upon previous work. In this paper, the importance of testing the robustness of recognition models is emphasized and it shows a simple way to improve it, which is a step towards creating robust pedestrian and object detection models.
Citations
-
2 3
CrossRef
-
0
Web of Science
-
2 4
Scopus
Authors (2)
Cite as
Full text
- Publication version
- Accepted or Published Version
- License
-
open in new tab
Keywords
Details
- Category:
- Articles
- Type:
- artykuły w czasopismach
- Published in:
-
IEEE Access
no. 8,
pages 136674 - 136683,
ISSN: 2169-3536 - Language:
- English
- Publication year:
- 2020
- Bibliographic description:
- Cygert S., Czyżewski A.: Toward Robust Pedestrian Detection With Data Augmentation// IEEE Access -Vol. 8, (2020), s.136674-136683
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/access.2020.3011356
- Sources of funding:
- Verified by:
- Gdańsk University of Technology
seen 182 times