Webinar: Domain Adaptation applied to Remote Sensing Data

Proponent: International Society of Photogrammetry and Remote Sensing (ISPRS)

Prof. Dr. Raul Feitosa
Prof. Dr. Raul Feitosa

Pontifícia Universidade Católica do Rio de Janeiro (PUC)

In the past decade, Deep Learning (DL) became the dominant trend in image data analysis, mostly due to the capacity of DL models to learn discriminative features directly from data, when labeled samples are abundant. 

At the same time, the availability of Earth observation (EO) data produced by RS systems has increased considerably. However, most of the RS applications still fall short in the demands imposed by DL-based techniques, basically because of the high costs required by field survey and labor-intensive visual interpretation to produce a large enough quantity of labeled data. The development of wide-reaching DL-based solutions for EO problems, therefore, remains a challenging problem.

In this sense, transfer learning is an attractive alternative, allowing the reuse of networks already trained on large data-sets in problems in which a limited quantity of labeled data is available. Such techniques, however, perform poorly when the domain shift phenomenon is significant. Considering EO applications, changes in the environmental conditions during the acquisition of new data, variations of objects’ appearances, geographical variability, and different sensor properties, domain shift makes it impossible to employ even fine-tuned classifiers over new data without a significant decrease in classification accuracy 

Domain adaptation techniques can be used to alleviate the domain shift problem. In short, domain adaptation aims at minimizing the discrepancy between distributions of two different domains. One of the distributions characterizes the data used to train a classifier; the other is associated with data that the classifier has never seen, which may present several of the aforementioned variations.

This SBSR Thematic Session aims at describing and discussing some state-of-the-art Domain Adaptation techniques applied to Earth observation data, such as feature adaptation and image translation.

TimeTitle of TalkSpeaker
9:00OpeningProf. Dr. Raul Feitosa (PUC-Rio)
9:05Welcome speech (per video)Prof. Dr. Christian Heipke (ISPRS President) 
9:40Strategies for Transfer Learning in Deep Learning for Remote Sensing applicationsProf. Dr. Franz Rottensteiner (University of Hanover, Germany)
10:20Domain adaptation for the classification of remote sensing imagery using adversarial training and entropy minimization.M. Sc. Dennis Wittich(University of Hanover, Germany)
10:50Domain Adaptation applied to Deforestation Monitoring Prof. Dr. Gilson Costa (UERJ)
11:20Panel Discussionall
11:40ClosingProf. Dr. Raul Feitosa (PUC-Rio)
Coordenação (Chair) / Palestrantes (Speakers)
Prof. Dr. Raul Feitosa
Prof. Dr. Raul Feitosa

Possui graduação em Engenharia Eletrônica pelo Instituto Tecnológico de Aeronáutica (ITA) (1979), mestrado em Engenharia Eletrônica pelo ITA (1983), doutorado em Ciência da Computação pela Universidade de Erlangen-Nürnberg, Alemanha (1988). Concluiu estágio pós-doutoral na Universidade de Hanover, Alemanha, em 2015. Atualmente é Professor Associado do programa de pós-graduação do Departamento de Engenharia Elétrica da Pontifícia Universidade Católica do Rio de Janeiro (PUC-Rio). É membro sênior da IEEE- Geoscience and Remote Sensing Society (IEEE-GRSS) e da International Society of Photogrammetry and Remote Sensing (ISPRS). 

M. Sc. Dennis Wittich
M. Sc. Dennis Wittich

Bachelor of Science: Civil and Environmental Engineering Leibniz Universität Hannover. Master of Science: Navigation and Field Robotics Leibniz Universität Hannover. Researcher and PhD-Student: Institute of Photogrammetry and Geoinformation
Leibniz Universität Hannover.

Prof. Dr. Christian Heipke
Prof. Dr. Christian Heipke

Christian Heipke is a professor of photogrammetry and remote sensing at Leibniz Universität Hannover, where
he currently leads a group of about 25 researchers. His professional interests comprise all aspects of photogrammetry, remote sensing, image understanding and their connection to computer vision and GIS. His has authored or co-authored more than 300 scientific papers, more than 70 of which appeared in peer-reviewed international journals. He also supervised close to 40 PhD candidates as main supervisor.
He is the recipient of the 1992 Otto von Gruber Award, the 2012 Fred Doyle Award, both from the International Society of Photogrammetry and Remote Sensing (ISPRS), and the 2013 Photogrammetric (Fairchild) Award from ASPRS. He is an ordinary member of various learnt societies incl. DGK (German Geodetic Commission), acatech (German Academy for Technical Sciences), and IAA (International Academy of Astronautics).
From 2004 to 2009, he served as vice president of EuroSDR (European Spatial Data Research, formerly known as OEEPE). From 2011-2014 he was chair of the German Geodetic Commission (DGK), from 2012-2016 ISPRS Secretary General. Currently he serves as ISPRS President.

Prof. Dr. Franz Rottensteiner
Prof. Dr. Franz Rottensteiner

Franz Rottensteiner received a Dipl.-Ing. degree in surveying, a Ph.D. degree and a venia docendi in Photogrammetry from Vienna University of Technology, Vienna, Austria (TUW). Currently, he is an Associate Professor and leader of the research group “Photogrammetric Image Analysis” at the Institute of Photogrammetry and GeoInformation at the University of Hannover, Germany (LUH). His research interests include all aspects of image orientation, image classification, automated object detection and reconstruction from images and point clouds, and change detection from remote sensing data. Before joining LUH in 2008, he worked as a postdoctoral researcher at TUW and the Universities of New South Wales and Melbourne, both in Australia. He has authored or co-authored more than 100 scientific papers, more than 35 of which have appeared in peer-reviewed international journals. He received the Karl Rinner Award of the Austrian Geodetic Commission in 2004 and the Carl Pulfrich Award for Photogrammetry, sponsored by Leica Geosystems, in 2017. Since 2011, he has been the Associate Editor of the ISI-listed journal “Photogrammetrie Fernerkundung Geoinformation” of the German Society of Photogrammetry, Remote Sensing and Geoinformation. Being the Chairman of the working group II/4 of the International Society of Photogrammetry and Remote Sensing (ISPRS), he has initiated and conducted the ISPRS benchmark on urban object detection and 3D building reconstruction.

Prof. Dr. Gilson Costa
Prof. Dr. Gilson Costa

Gilson Alexandre Ostwald Pedro da Costa holds a Bachelor Degree in Computer Engineering from the Catholic University of Rio de Janeiro (PUC-Rio), obtained in 1991, having afterwards specialized professionally in the development of geographic information systems and remote sensing applications. He holds a Master’s Degree in Computer Engineering, with emphasis on Geomatics, from the Rio de Janeiro State University (UERJ), obtained in 2003. He also holds a PhD degree in Electrical Engineering from PUC-Rio, having concluded his PhD research in 2009, which was partially developed in a doctoral internship at the Institut für Informationsverarbeitung (TNT) of the Leibniz Hannover University.