AKCMamba-YOLO：用于实时目标检测的选择性状态空间模型
AKCMamba-YOLO: Selective State Space Models For Real-Time Object Detection
将线性复杂度的选择性状态空间模型（SSM）引入YOLO架构，为实时目标检测提供替代注意力机制的全局建模方案，可复用于需要长程依赖但计算受限的检测场景。
原文依据 we propose AKCMamba-YOLO, a novel object detector that incorporates SSM into the YOLO architecture
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论YOLO（You Only Look Once）系列一直是实时目标检测的基石，以其高效的卷积设计和快速推理而闻名。然而，其对卷积操作的依赖本质上限制了捕获长程依赖和丰富上下文信息的能力，导致在复杂场景中性能欠佳。最近，状态空间模型（SSM）作为注意力机制的高效替代方案出现，以线性时间复杂度提供全局表示。本文提出AKCMamba-YOLO，一种将SSM融入YOLO架构的新型目标检测器。我们引入3CAKCMamba和4CAKCMamba模块到新的目标检测框架中，实现增强的通道交互和跨层语义融合。该设计在保持计算效率的同时改进了多尺度特征建模。为支持安全关键应用，我们提供了铁路行人检测数据集，包含复杂场景下2,975张标注图像。在COCO2017、电力塔异物检测数据集和我们的自定义数据集上的实验表明，AKCMamba-YOLO相比最优基线实现了更高的精度和速度，使其非常适合实时和资源受限环境。
英文原文摘要 1301 字符
The YOLO (You Only Look Once) series has been a cornerstone in real-time object detection, renowned for its efficient convolutional design and rapid inference. However, its reliance on convolutional operations inherently limits its ability to capture long-range dependencies and rich contextual information, leading to suboptimal performance in complex scenes. Recently, SSM (State Space Models) have emerged as an efficient alternative to attention mechanisms, offering global representation with linear time complexity. In this paper, we propose AKCMamba-YOLO, a novel object detector that incorporates SSM into the YOLO architecture. We introduce 3CAKCMamba and 4CAKCMamba modules to a novel object detection framework, enabling enhanced channel interaction and cross-layer semantic fusion. This design improves multi-scale feature modeling while maintaining computational efficiency. To support safety-critical applications, we provide railway pedestrian Detection datasets with 2,975 annotated images under complex scenarios. Experiments on COCO2017, power tower foreign object detection datasets, and our custom dataset show that AKCMamba-YOLO achieves superior accuracy and speed compared to state-of-the-art baselines, making it well-suited for real-time and resource-constrained environments.