We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
BSMH: Cross‐dataset object detection based on box‐separated multiple‐head.
- Authors
Lu, Feng; Xu, You Chun; Qi, Yao; Xie, De Sheng; Le Li, Yogn
- Abstract
Cross‐dataset object detection methods can adapt to the needs of rapid category expansion in object detection tasks. However, these methods are prone to generate dataset‐aware errors with false alarm objects. This study is aimed to address these issues. A box‐separated multiple‐head module and box‐separated loss function based on the YOLOv8 network are devised to achieve cross‐dataset object detection. Additionally, a sameclass‐aware fusion module to avoid gradient conflicts due to cross‐category conflicts is developed. A multiple‐head fusion module is devised to reduce the number of false alarm objects caused by dataset‐aware errors. A global class‐aware sampler is also designed to adapt to the impact of the imbalanced number of categories and training samples across datasets. The effectiveness of the box‐separated multiple‐head module is verified using cross‐datasets built using the COCO, WiderFace, WiderPerson, and OpenImages V4 datasets. Extensive experiments demonstrate the efficiency and precision of the proposed method.
- Subjects
OBJECT recognition (Computer vision); COMPUTER vision; FALSE alarms
- Publication
IET Image Processing (Wiley-Blackwell), 2024, Vol 18, Issue 11, p3013
- ISSN
1751-9659
- Publication type
Article
- DOI
10.1049/ipr2.13152