Intelligent Detection Using Convolutional Neural Network (ID-CNN)
Intelligent Detection Using Convolutional Neural Network (ID-CNN)
复制标题
使用卷积神经网络（ID-CNN）进行智能检测
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Muhammad Sohail Sardar
中科院分区：
文献类型：
--
作者：
Amish Jahangir Kapoor;Hong Fan;Muhammad Sohail Sardar
在本文中，我们将研究最先进的目标检测技术（即Faster R-CNN）的基本流程和原理，并通过将两种策略纳入其中进一步改进。首先，我们提出了一种使用连接层的多层特征合并策略。其次，我们引入了一种快速R-CNN的上下文学习方案。以前，Faster R-CNN只使用区域特征。上下文特征与区域特征一起被添加到分类和检测任务中。我们对更快R-CNN的改进显示出令人鼓舞的结果。我们将改进后的更快R-CNN网络称为ID-CNN (Intelligent Detection Using Convolutional Neural network)，因为它的检测精度更高。因此，我们称它为智能探测器。我们使用深度VGG-16模型作为基础模型，就像Faster R-CNN所做的那样。我们在Pascal VOC公共数据集上评估了我们的ID-CNN。实验结果表明，ID-CNN能在一定程度上有效提高目标检测的平均精度。在2007年和2012年，我们的平均精度（mAP）分别达到74.7%和71.9%。ID-CNN也是端到端可训练的，采用了与Faster R-CNN相同的交替微调优化方案。最后，我们将ID-CNN与Faster R-CNN在ImageNet目标检测数据集上进行对比，得到了48.1%的mAP，而Faster R-CNN的mAP为46.2%。
In this paper, we will study the basic flow and the principle of state-of-the-art object detection technique (i.e. Faster R-CNN) and improve it further with the inclusion of two strategies into it. Firstly, we propose a multi-layer features merging strategy by using a concatenation layer. Secondly, we introduce a contextual learning scheme for Faster R-CNN. Previously, Faster R-CNN just uses regional features. Contextual features are added with the regional features for the classification and detection task. Our improvement on Faster R-CNN shows promising results. We call our improved Faster R-CNN network as ID-CNN (Intelligent Detection Using Convolutional Neural Network) as its detection accuracy is better. Therefore, we call it as an intelligent detector. We use a deep VGG-16 model as our base model, as Faster R-CNN did. We evaluated our ID-CNN on Pascal VOC public datasets. Experimental results show that ID-CNN can effectively improve the object detection average precision to some extent. On VOC 2007 and 2012, we achieved a mean average precision (mAP) of 74.7% and 71.9%, respectively. ID-CNN is also end-to-end trainable with the same alternating fine-tuning optimization scheme of Faster R-CNN. Finally, we compared ID-CNN with Faster R-CNN on ImageNet object detection dataset and we achieved mAP of 48.1% compared with 46.2% for Faster R-CNN.