Abstract
Rotated bounding boxes drastically reduce output ambiguity of elongated objects, making it superior to axis-aligned bounding boxes. Despite the effectiveness, rotated detectors are not widely employed. Annotating rotated bounding boxes is such a laborious process that they are not provided in many detection datasets where axis-aligned annotations are used instead. In this paper, we propose a framework that allows the model to predict precise rotated boxes only requiring cheaper axis-aligned annotation of the target dataset 1. To achieve this, we leverage the fact that neural networks are capable of learning richer representation of the target domain than what is utilized by the task. The under-utilized representation can be exploited to address a more detailed task. Our framework combines task knowledge of an out-of-domain source dataset with stronger annotation and domain knowledge of the target dataset with weaker annotation. A novel assignment process and projection loss are used to enable the cotraining on the source and target datasets. As a result, the model is able to solve the more detailed task in the target domain, without additional computation overhead during inference. We extensively evaluate the method on various target datasets including fresh-produce dataset, HRSC2016 and SSDD. Results show that the proposed method consistently performs on par with the fully supervised approach.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 |
Editors | Eric Mortensen |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 15518-15527 |
Number of pages | 10 |
ISBN (Electronic) | 9798350301298 |
ISBN (Print) | 9798350301304 |
DOIs | |
Publication status | Published - 2023 |
Event | IEEE Conference on Computer Vision and Pattern Recognition 2023 - Vancouver, Canada Duration: 18 Jun 2023 → 22 Jun 2023 https://cvpr2023.thecvf.com/ (Website) https://openaccess.thecvf.com/CVPR2023?day=all (Proceedings) https://ieeexplore.ieee.org/xpl/conhome/10203037/proceeding (Proceedings) https://cvpr2023.thecvf.com/Conferences/2023 (Website) |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Volume | 2023-June |
ISSN (Print) | 1063-6919 |
Conference
Conference | IEEE Conference on Computer Vision and Pattern Recognition 2023 |
---|---|
Abbreviated title | CVPR 2023 |
Country/Territory | Canada |
City | Vancouver |
Period | 18/06/23 → 22/06/23 |
Internet address |
|
Keywords
- detection
- Recognition: Categorization
- retrieval