Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

Aerial Scene Classification through Fine-Tuning with Adaptive Learning Rates and Label Smoothing

Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained C...

Full description

Bibliographic Details
Main Authors: Biserka Petrovska, Tatjana Atanasova-Pacemska, Roberto Corizzo, Paolo Mignone, Petre Lameski, Eftim Zdravevski
Format: Article
Language:English
Published: MDPI AG 2020-08-01
Series:Applied Sciences
Subjects:
remote sensing
convolutional neural network
fine-tuning
learning rate scheduler
cyclical learning rates
label smoothing
Online Access:https://www.mdpi.com/2076-3417/10/17/5792

Internet

https://www.mdpi.com/2076-3417/10/17/5792

Similar Items