We are pleased to invite you to a talk by Ronny Hänsch, from DLR Germany.

Shallow learners are dead – Long live shallow learners! Random Forests in the age of Deep Learning

WHEN: 26 November 2020, 15:00-16:00.

WHERE: Click here to join the Teams meeting or in the CIRFA corridor. 



The rise of deep neural networks has caused essential changes well beyond the machine learning (ML) and computer vision (CV) communities. One of the consequences is that the previous zoo of used ML methods (e.g. Naive Bayes, MLPs, SVMs, Random Forests, etc.) is now replaced by a monoculture of (deep) neural networks. Deep Learning (DL) approaches have also been successfully used (and sometimes abused) in Remote Sensing (RS) and Earth Observation (EO). Nevertheless, in contrast to other CV applications, shallow learners seem to prevail in RS/EO and coexist with DL (although somewhat in the shadow). This talk aims to shed some light on possible reasons, discusses modern RFs variations, and positions them into the context of Deep Learning.


Ronny Hänsch received the Diploma degree in computer science and the Ph.D. degree from the Technische Universität Berlin, Berlin, Germany, in 2007 and 2014, respectively. From 2019, he works as senior researcher at the German Aerospace Center. His research interests include computer vision, machine learning, object detection, neural networks, and ensemble theory. He worked in the field of image-based object detection and classification with a focus on remote sensing data and in particular polarimetric synthetic aperture radar images as well as image-based 3D reconstruction. He organized multiple tutorials on Machine Learning in Remote Sensing at international conferences (e.g. IGARSS, EUSAR, Whispers). He currently serves as Associate Editor of the IEEE Geoscience and Remote Sensing Letters and as co-chair of the ISPRS Working Group II/1 Image Orientation as well as of the IEEE GRSS Technical Committee Image Analysis and Data Fusion.


Malin, Thomas & Andrea