• Prof. Dr. Ir. Aleksandra Pizurica, Department Telecommunications and Information Processing, Research Group for Artificial Intelligence and Sparse Modelling, Ghent University. Website: telin.ugent.be/~sanja/

Title: Sparse coding and deep learning in the analysis of hyperspectral images in remote sensing

Abstract: Hyperspectral imaging is now established as one of the key technologies in Earth observation. While offering rich spectral information in hundreds of spectral bands, hyperspectral images remain to pose challenges for processing due to their huge dimensionality and lack of sufficient training data to match it. In this talk we address mainly clustering and classification of large-scale remotely sensed hyperspectral images, from perspectives of sparse coding and deep learning. Recent results in subspace clustering of very large scale data will be presented and discussed, including clustering of multi-source data. We also address limitations of current deep learning models based on convolutional neural networks (CNN) in hyperspectral image analysis and we discuss recent models based on group CNN designs that require less training data and generalize better to different data sets.

• Prof. Dr. Devis Tuia, EPFL ENAC, Environmental Computational Science and Earth Observation Laboratory (ECEO). Website: sites.google.com/site/devistuia/

Title: Making sense of geospatial data with deep learning … while interacting with people

Abstract: With remote sensing and geo-information data entering more and more our daily life, products need to be of great precision. Deep learning algorithms have been used increasingly to provide such products, but they greatly rely on high quality annotations, which are difficult to obtain for unconventional application. Moreover, since awareness of such data has become high, one expects simpler ways to access and interact with remote sensing. In this talk, I will discuss strategies one can use to make remote sensing more accessible, useful and fun.