BSMH: Cross-dataset object detection based on box-separated multiple-head

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. Cross-dataset object detection methods can adapt to the needs of rapid category expansion in object detection tasks. However, these methods is prone to generate dataset-aware errors with false alarm objects. A box-separated multiple-head module and box-separated loss function based on the YOLOv8 network are devised to achieve cross-dataset object detection. image