论文标题
poly-Yolo：更高的速度，更精确的检测和Yolov3的实例分割
Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
论文作者
论文摘要
我们提出了一个新版本的Yolo，具有更好的性能，并以称为Poly-Yolo的实例细分进行扩展。 Poly-Yolo建立在Yolov3的原始思想的基础上，并消除了其两个弱点：大量的重写标签和锚定效率低下的分布。 Poly-Yolo通过使用阶梯上的UPSMPLING从光Se-Darknet-53主链中汇总特征来减少问题，并产生具有高分辨率的单尺度输出。与Yolov3相比，Poly-Yolo只有60％的可训练参数，但将MAP提高了40％。我们还提出了较少的参数和较低输出分辨率的聚Yolo Lite。它具有与Yolov3相同的精度，但要快三倍，因此适用于嵌入式设备。最后，Poly-Yolo使用边界多边形进行实例分割。该网络经过训练，以检测在极地网格上定义的尺寸无关的多边形。每个多边形的顶点都以其置信度预测，因此多Yolo产生的多边形具有不同的顶点。
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Darknet-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves mAP by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation using bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore Poly-YOLO produces polygons with a varying number of vertices.
