• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Artificial Neural Networks >PA-RetinaNet: Path Augmented RetinaNet for Dense Object Detection
【24h】

PA-RetinaNet: Path Augmented RetinaNet for Dense Object Detection

机译：PA-RetinaNet：用于密集物体检测的增强路径RetinaNet

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Object detection methods can be divided into two categories that are the two-stage methods with higher accuracy but lower speed and the one-stage methods with lower accuracy but higher speed. In order to inherit the advantages of both approaches, a novel dense object detector, called Path Augmented RetinaNet (PA-RetinaNet), is proposed in this paper. It not only achieves a better accuracy than the two-stage methods, but also maintains the efficiency of the one-stage methods. Specifically, we introduce a bottom-up path augmentation module to enhance the feature exaction hierarchy, which shortens the information path between lower feature layers and topmost layers. Furthermore, we address the class imbalance problem by introducing a Class-Imbalance loss, where the loss of each training sample is weighted by a function of its predicted probability, so that the trained model focuses more on hard examples. To evaluate the effectiveness of our PA-RetinaNet, we conducted a number of experiments on the MS COCO dataset. The results show that our method is 4.3% higher than the existing two-stage method, while the speed is similar to the state-of-the-art one-stage methods.
机译：物体检测方法可分为两类：精度较高但速度较慢的两步法和精度较低但速度较高的一步法。为了继承这两种方法的优点，本文提出了一种新颖的密集物体检测器，称为路径增强视网膜网（PA-RetinaNet）。它不仅比两阶段方法具有更高的精度，而且还保持了一阶段方法的效率。具体来说，我们引入了一个自下而上的路径增强模块，以增强特征精确度层次结构，从而缩短了较低特征层和最高层之间的信息路径。此外，我们通过引入类不平衡损失来解决类不平衡问题，其中，每个训练样本的损失都通过其预测概率的函数进行加权，因此，训练后的模型将重点更多地放在困难的示例上。为了评估PA-RetinaNet的有效性，我们对MS COCO数据集进行了许多实验。结果表明，我们的方法比现有的两阶段方法高4.3％，而速度与最新的一阶段方法相似。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号