首页> 外文OA文献 >Table 5: Accuracy of SVM classifier on DBAP features derived from pre-trained LeNet with DBAP layer. The DBAP features show better classification results than the MaxPool features in LeNet. The fully connected (FC) layers of LeNet with DBAP also tend to show better discrimination ability as compared to FC layer features extracted from regular LeNet on all benchmark data sets.

【2h】

Table 5: Accuracy of SVM classifier on DBAP features derived from pre-trained LeNet with DBAP layer. The DBAP features show better classification results than the MaxPool features in LeNet. The fully connected (FC) layers of LeNet with DBAP also tend to show better discrimination ability as compared to FC layer features extracted from regular LeNet on all benchmark data sets.

机译：表5：SVM分类器对具有DBAP层的预先训练的Lenet派生的DBAP特征的精度。 DBAP功能显示比LENET中的MAXPOOL功能更好的分类结果。与DBAP的完全连接（FC）LENET的层也倾向于显示与在所有基准数据集上从常规LENET提取的FC层特征相比显示出更好的辨别能力。

代理获取

本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。

页面导航

著录项
引文网络
相似文献
相关主题

著录项

作者

展开▼
作者单位

展开▼
年度 -1
总页数
原文格式 PDF
正文语种
中图分类

相似文献

外文文献

1. Analysis of the proficiency of fully connected neural networks in the process of classifying digital images. Benchmark of different classification algorithms on high-level image features from convolutional layers [J] . Janke Jonathan, Castelli Mauro, Popovic Ales Expert Systems with Application . 2019,第NOVa期

机译：分析全连接神经网络在数字图像分类过程中的熟练程度。不同分类算法在卷积层高级图像特征上的基准测试
2. Analysis of the proficiency of fully connected neural networks in the process of classifying digital images. Benchmark of different classification algorithms on high-level image features from convolutional layers [J] . Janke Jonathan, Castelli Mauro, Popovic Ales Expert systems with applications . 2019,第Nova期

机译：分析数字图像分类过程中完全连接神经网络的熟练程度分析。不同分类算法的基准从卷积层的高级图像特征
3. A Novel Classifier Ensample for Combining Pixel-Based and Object Based Classification Methods for Improving Feature Extraction from LIDAR Intensity Data and LIDAR Derived Layers [J] . Ayman El-Shehaby, Lamyaa Gamal El-Deen Taha American Journal of Geographic Information System . 2018,第3期

机译：结合基于像素和基于对象的分类方法的新型分类器样本，可改善从LIDAR强度数据和LIDAR派生层的特征提取
4. Table 7: Accuracy of k-NN classifier on DBAP features derived from pre-trained LeNet with DBAP layer. The results achieved are better than the ones obtained by MaxPool layer in a regular LeNet. The inclusion of DBAP layer also improves the FC features for discrimination task. [O] . -1

机译：表7：k-nn分类器的准确性DBAP功能从带有DBAP层的预先训练的Lenet派生的DBAP功能。所实现的结果优于MaxPool层在常规登记中获得的结果。包含DBAP层还可以改善FC特征进行歧视任务。

著录项

引文网络

相似文献

相关主题

期刊订阅