密集特征哈希的遥感场景分类
|
李国祥, 夏国恩, 白丽明, 马文斌
|
Remote sensing image classification based on DenseNet feature hashing
|
LI Guoxiang, XIA Guo’en, BAI Liming, MA Wenbin
|
|
表3 不同CNN模型的特征编码
|
Tab.3 Feature coding of different CNN models(%)
|
|
深度特征 | 迁移学习 | Bilinear | BOVW | VLAD | FV | 编码方法平均精度 | AlexNet | 89.80 | 80.40 | 89.50 | 90.30 | 92.50 | 88.18 | VGG19 | 92.00 | 90.70 | 92.60 | 93.30 | 93.40 | 92.50 | Google | 92.50 | 90.30 | 84.00 | 89.50 | 87.70 | 87.88 | Resnet50 | 95.50 | 93.30 | 90.00 | 89.90 | 90.40 | 90.90 | DenseNet | 96.70 | | | | | | DenseBlock1 | | 54.10 | 78.86 | 84.57 | 87.81 | 76.34 | DenseBlock2 | | 71.62 | 85.24 | 87.14 | 92.38 | 84.10 | DenseBlock3 | | 90.76 | 91.90 | 92.76 | 95.05 | 92.62 | DenseBlock4 | | 95.24 | 93.90 | 92.29 | 93.14 | 93.64 | 本文算法 | | | | | | 98.21 |
|
|
|