| 朱阳光,刘瑞敏,黄琼桃.基于深度神经网络的弱监督信息细粒度图像识别[J].电子测量与仪器学报,2020,34(2):115-122 |
| 基于深度神经网络的弱监督信息细粒度图像识别 |
| Fine grained image recognition of weak supervisory information based on deep neural network |
| |
| DOI： |
| 中文关键词: 细粒度图像分类 深度学习 图像识别 卷积神经网络 |
| 英文关键词:fine-grained image categorization deep learning image recognition convolution neural network |
| 基金项目:国家自然科学基金（61863018）资助项目 |
|
|
|
|
| 摘要点击次数: 488 |
| 全文下载次数: 3 |
| 中文摘要: |
| 强监督识别算法需要大量的人工标注信息，消耗较多的人力物力资源。为了解决上述问题，满足实际需求，提出了两种基于弱监督信息图像识别方法用于细粒度图像分类(FGVC)。一种是联合残差网络和Inception网络，通过优化卷积神经网络的网络结构提高捕捉细粒度特征的能力。另一种是对双线性CNN模型进行改进，特征提取器选取Google提出的Inception v3模组和Inception v4模组，最后把不同的局部特征汇集起来进行分类。通过在CUB200 2011鸟类公开数据集和Stanford Cars汽车类型数据集上进行测试，实验结果表明，提出的方法在两种数据集上的分类精度分别到达了883%和942%的分类精度，实现了较好的分类性能。 |
| 英文摘要: |
| Strong supervisory recognition algorithm requires a large amount of annotation information and consumes a lot of manpower and material resources. In order to solve the above problems and meet the practical requirements, two image recognition methods based on weak supervisory information are proposed for fine grained vision classification (FGVC). One is the combination of ResNet and Inception network, which improves the ability of capturing fine grained features by optimizing the network structure of convolutional neural network. The other is to improve the Bilinear CNN model, feature extractor selects Inception v3 module and Inception v4 module proposed by Google, and finally gathers different local features for classification. The experimental results on CUB200-2011 and Stanford Cars fine grained image datasets show that the proposed method achieves classification accuracy of 883% and 942% on the two data sets, and achieves better classification performance. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
