DropBand:A Simple and Effective Method for Promoting the VHR Scene Classification Accuracy of CNN
文章链接：http://ieeexplore.ieee.org/document/8248633/ 遥感图像场景分类的难点主要在于，类内的差异性和类间的相似性。所以分类的精度一直不高。而在已有的数据集如：RSSCN7,UC-Merced 等数据集上分类精度可以达到94%-96%左右(finetune)，这与数据集本身的特点有关。如：数据集本身比较简单，或使用的训练集所占比例比较大。想要再进一步提高
相关文章
- 1. A Simple but Effective Classification Model for Grammatical Error Correction
- 2. A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION
- 3. Hyperspectral Image Classification in the Presence of Noisy Labels
- 4. Comparison of SIFT Encoded and Deep Learning Features for the Classification and Detection of Esca D
- 5. A Simple yet Effective Way for Improving the Performance of GANs
- 6. [转] Implementing a CNN for Text Classification in TensorFlow
- 7. Semantic Flow for Fast and Accurate Scene Parsing
- 8. (2020.04) Review: YOLOv4: Optimal Speed and Accuracy of Object Detection
- 9. The use of sort() method, sorted() function and reverse() method
- 10. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- 更多相关文章...
- • Scala for循环 - Scala教程
- • XSL-FO simple-page-master 对象 - XSL-FO 教程
- • RxJava操作符（七）Conditional and Boolean
- • Java 8 Stream 教程
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. A Simple but Effective Classification Model for Grammatical Error Correction
- 2. A NEW METHOD OF REGION EMBEDDING FOR TEXT CLASSIFICATION
- 3. Hyperspectral Image Classification in the Presence of Noisy Labels
- 4. Comparison of SIFT Encoded and Deep Learning Features for the Classification and Detection of Esca D
- 5. A Simple yet Effective Way for Improving the Performance of GANs
- 6. [转] Implementing a CNN for Text Classification in TensorFlow
- 7. Semantic Flow for Fast and Accurate Scene Parsing
- 8. (2020.04) Review: YOLOv4: Optimal Speed and Accuracy of Object Detection
- 9. The use of sort() method, sorted() function and reverse() method
- 10. SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition