You Only Look Once (YOLO)-based object detectors have shown remarkable accuracy for automated brain tumor detection. In this paper, we develop a novel BGF-YOLO architecture by incorporating Bi-level Routing Attention (BRA), Generalized feature pyramid networks (GFPN), and Fourth detecting head into YOLOv8. BGF-YOLO contains an attention mechanism to focus more on important features, and feature pyramid networks to enrich feature representation by merging high-level semantic features with spatial details. Furthermore, we investigate the effect of different attention mechanisms and feature fusions, detection head architectures on brain tumor detection accuracy. Experimental results show that BGF-YOLO gives a 4.7% absolute increase of mAP$_{50}$ compared to YOLOv8x, and achieves state-of-the-art on the brain tumor detection dataset Br35H. The code is available at https://github.com/mkang315/BGF-YOLO.

翻译：基于YOLO（You Only Look Once）的目标检测器在自动化脑肿瘤检测中展现出了卓越的精度。本文通过将双层路由注意力（Bi-level Routing Attention, BRA）、广义特征金字塔网络（Generalized feature pyramid networks, GFPN）和第四检测头融入YOLOv8，提出了一种新型BGF-YOLO架构。BGF-YOLO包含一个注意力机制，用于聚焦于重要特征，并通过融合高层语义特征与空间细节来增强特征表示的特征金字塔网络。此外，我们研究了不同注意力机制、特征融合方式及检测头架构对脑肿瘤检测精度的影响。实验结果表明，与YOLOv8x相比，BGF-YOLO的mAP$_{50}$绝对提升了4.7%，并在脑肿瘤检测数据集Br35H上达到了当前最优性能。代码已开源至https://github.com/mkang315/BGF-YOLO。