Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification.
Yakoub BaziMohamad Mahmoud Al RahhalHaikel Al-HichriNaif AlajlanPublished in: Remote. Sens. (2019)
Keyphrases
- remote sensing
- scene classification
- fine tuning
- indoor outdoor
- image classification
- object recognition
- multi spectral images
- change detection
- remote sensing images
- hyperspectral
- natural scenes
- multispectral
- remote sensing imagery
- hyperspectral data
- visual words
- image analysis
- land cover classification
- biologically inspired
- image processing
- satellite images
- hyperspectral images
- image fusion
- remote sensing data
- image representation
- satellite data
- automatic image registration
- high resolution
- remotely sensed data
- land cover
- feature space
- pattern recognition
- earth observation
- bag of features
- text classification
- co occurrence
- high quality
- feature extraction
- feature selection
- hyperspectral remote sensing
- neural network
- image structure
- infrared
- natural images
- image features
- multiresolution
- feature vectors
- pairwise
- multiscale
- machine learning