arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.09203cs.CVcs.LGcs.NEeess.IV
收藏

用于高精度目标检测的模块化网络

Modular network for high accuracy object detection

Erez Yahalomi

摘要:

我们提出了一种新的模块化目标检测卷积神经网络,显着提高了目标检测的准确性。该网络由两个层次结构的阶段。第一阶段是检测一般类的网络。第二阶段由单独的网络组成,以细化每个通用类对象的分类和定位。与现有技术的目标检测网络相比,模块化网络中的分类误差提高了大约3-5倍,从12%提高到2.5%-4.5%。该网络易于实现,具有0.94 mAP。网络架构可以是提高现有技术的目标检测网络和其他种类的深度学习网络的广泛状态的准确性的平台。我们发现,通过迁移学习初始化的深度学习网络变得更准确,因为它后来训练检测的类的数量变得更少。

英文摘要:

We present a novel modular object detection convolutional neural network that significantly improves the accuracy of object detection. The network consists of two stages in a hierarchical structure. The first stage is a network that detects general classes. The second stage consists of separate networks to refine the classification and localization of each of the general classes objects. Compared to a state of the art object detection networks the classification error in the modular network is improved by approximately 3-5 times, from 12% to 2.5 %-4.5%. This network is easy to implement and has a 0.94 mAP. The network architecture can be a platform to improve the accuracy of widespread state of the art object detection networks and other kinds of deep learning networks. We show that a deep learning network initialized by transfer learning becomes more accurate as the number of classes it later trained to detect becomes smaller.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑