DC Field | Value | Language |
---|---|---|
dc.contributor.author | Si, Wenwen | - |
dc.contributor.author | Li, Shuo | - |
dc.contributor.author | Park, Sangdon | - |
dc.contributor.author | Lee, Insup | - |
dc.contributor.author | Bastani, Osbert | - |
dc.date.accessioned | 2024-02-01T01:53:34Z | - |
dc.date.available | 2024-02-01T01:53:34Z | - |
dc.date.created | 2024-01-30 | - |
dc.date.issued | 2023-06-22 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/120005 | - |
dc.description.abstract | Deep learning models have shown extreme vulnerability to distribution shifts such as synthetic perturbations and spatial transformations. In this work, we explore whether we can adopt the characteristics of adversarial attack methods to help improve robustness of object detection to distribution shifts such as synthetic perturbations and spatial transformations. We study a class of realistic object detection settings wherein the target objects have control over their appearance. To this end, we propose a reversed Fast Gradient Sign Method (FGSM) to obtain these angelic patches that significantly increase the detection probability, even without pre-knowledge of the perturbations. In detail, we apply the patch to each object instance simultaneously, strengthening not only classification, but also bounding box accuracy. Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem. More importantly, the performance is also transferable to different detection models even under severe affine transformations and deformable shapes. To the best of our knowledge, we are the first object detection patch that achieves both cross-model efficacy and multiple patches. We observed average accuracy improvements of 30% in the real-world experiments. Our code is available at: https://github.com/averysi224/angelic-patches. | - |
dc.language | English | - |
dc.publisher | IEEE Computer Society | - |
dc.relation.isPartOf | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.relation.isPartOf | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Angelic Patches for Improving Third-Party Object Detector Performance | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, pp.24638 - 24647 | - |
dc.citation.conferenceDate | 2023-06-18 | - |
dc.citation.conferencePlace | CA | - |
dc.citation.endPage | 24647 | - |
dc.citation.startPage | 24638 | - |
dc.citation.title | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 | - |
dc.contributor.affiliatedAuthor | Park, Sangdon | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.