Machine Learning in Remote Sensing “Best practices and recent solutions” tutorial @ IGARSS 2019
Despite the wide and often successful application of machine learning techniques to analyse and interpret remotely sensed data, the complexity, special requirements, as well as selective applicability of these methods often hinders to use them to their full potential. The gap between sensor- and application-specific expertise on the one hand, and a deep insight and understanding of existing machine learning methods often leads to suboptimal results, unnecessary or even harmful optimizations, and biased evaluations. The aim of this tutorial is twofold: First, spread good practices for data preparation: Inform about common mistakes and how to avoid them (e.g. dataset bias, non-iid samples), provide recommendations about proper preprocessing and initialization (e.g. data normalization), and state available sources of data and benchmarks. Second, present efficient and advanced machine learning tools: Give an overview of standard machine learning techniques and when to use them (e.g. standard regression and classification techniques, clustering, etc.), as well as introducing the most modern methods (such as random fields, ensemble learning, and deep learning).
Tutorial Learning Objectives:
- Overview of standard machine learning approaches (naive Bayes, Linear Discriminant Analysis, Support Vector Machines) and how to use them
- Performance evaluation (correct sampling, cross-validation, iid data, metrics, data and benchmarks)
- Introduction to sophisticated methods (Random Forests, Markov and Conditional Random Fields, Convolutional Neural Networks)
Materials and Requirements:
Slides will be made available online before the tutorial. A website will be set up for downloads and additional resources.
The tutorial will collaborate with the Code Workshop where specific methods can be tested hands on.
|9.30am - 11.00am||Part I - Classical approaches to machine learning (Ronny Hänsch)||Slides 1|
|11.00am - 11.15am||coffee break|
|11.15am - 12.45am||Part II - Features and Deep Learning (Yuliya Tarabalka)||Slides 2|
|12.45am - 14.15am||lunch break|
|14.15am - 15.45am||Part III - Random Fields (Devis Tuia)||Slides 3|
|15.45am - 16.00am||coffee break|
|16.00am - 17.30am||Part IV - Deep Learning (Bertrand Le Saux)||Slides 4|