Recently, anchor-free methods have brought new ideas to the field of object detection that eliminate the need for anchor boxes in object detection and provide a simpler detection structure. CenterNet is the representative anchor-free method. However, this method still has the problem of obtaining high-resolution representation from low-resolution representation using upsampling, and the predicted heatmap is not accurate enough in space and does not make full use of the shallow low-level features of the network. We introduce CenterNet-HRA to solve this problem. An attention module is proposed to calibrate the high-level semantic features of the network output using the shallow low-level features from different receptive fields; HRNet is used as the backbone to maintain high-resolution feature representation through the whole process rather than using upsampling to generate high-resolution feature representation as HourglassNet. Considering that the feature representations with different resolutions have different contributions to the network but HRNet fuses them without distinction, a novel weighted feature fusion HRNet is designed to achieve higher detection precision. Our method achieves an average precision (AP) of 42.3% at 13.5 frames-per-second (FPS) (40.3% AP at 13.3 FPS for CenterNet-HG) on the MS-COCO benchmark.

中文翻译：

---

用于目标检测的加权特征融合和注意机制

近来，无锚的方法将新的思想带入了物体检测领域，从而消除了在物体检测中对锚框的需求，并提供了一种更简单的检测结构。CenterNet是典型的免锚方法。但是，该方法仍然存在使用上采样从低分辨率表示中获得高分辨率表示的问题，并且预测的热图在空间上不够准确，并且没有充分利用网络的浅层低层特征。我们引入CenterNet-HRA来解决此问题。提出了一个注意模块，利用来自不同接受领域的浅层低层特征来校准网络输出的高层语义特征；HRNet被用作在整个过程中维护高分辨率特征表示的主干，而不是使用上采样来生成高分辨率特征表示（如HourglassNet）。考虑到具有不同分辨率的特征表示对网络的贡献不同，但是HRNet毫无区别地融合了它们，因此设计了一种新颖的加权特征融合HRNet，以实现更高的检测精度。我们的方法在MS-COCO基准上以13.5帧/秒（FPS）的平均精度（AP）达到42.3％（对于CenterNet-HG，在13.3 FPS的情况下达到40.3％的AP）。设计了一种新颖的加权特征融合HRNet，以实现更高的检测精度。我们的方法在MS-COCO基准上以13.5帧/秒（FPS）的平均精度（AP）达到42.3％（对于CenterNet-HG，在13.3 FPS的情况下达到40.3％的AP）。设计了一种新颖的加权特征融合HRNet，以实现更高的检测精度。我们的方法在MS-COCO基准上以13.5帧/秒（FPS）的平均精度（AP）达到42.3％（对于CenterNet-HG，在13.3 FPS的情况下达到40.3％的AP）。