Home
All Courses
About
Partner
All Courses
•
AI for landcover classification
•
Interpretability of the Activation Space
Back to course
Back to all courses
Lessons
Introduction to Remote Sensing
4:50
Introduction to Land Cover Classification
22:43
Benchmark Dataset
4:00
Contrastive self-supervised Learning
4:31
Introduction to GEE via Code Snippets Walkthrough
5:14
Introduction to Atmospheric Transformation
4:24
Location-Based Labels
1:50
The Basic Idea of ASOS
1:48
The Neural Network Architecture and Training
1:53
Defining Occlusions Using the Activation Space
3:46
Interpretability of the Activation Space
1:06
The Advantages of ASOS
2:03
Datasets - AnthroProtect
3:58
Datasets - MapInWild
2:56
Datasets - TorchGeo
3:50
Datasets - BigEarthNet
3:30
Datasets - Eurosat
2:24
Spatial Data Split
2:50
Interpretability of the Activation Space
The activation space makes the neural network more transparent and interpretable.
Lecturer
s
•
Ankit Patnala
•
Ribana Roscher
•
Timo Stomberg
Additional Material
Additional Material
Additional Material
