Prochain Meetup

#18.07 - Deep learning and aerial and satellite images
• Yuliya Tarabalka (INRIA-Titane): "Can we classify the world? Where Deep Learning Meets Remote Sensing" Deep learning has been recently gaining significant attention for the analysis of data in multiple domains. It seeks to model high-level knowledge as a hierarchy of concepts. With the exploding amount of available data, the improvement of hardware and the advances in training methodologies, now such hierarchies can contain many more processing layers than before, hence the adoption of the term "deep". In remote sensing, recent years have witnessed a remarkable increase in the amount of available data, due to a consistent improvement in the spectral, spatial and temporal resolutions of the sensors. Moreover, there are new sources of large-scale open access imagery, governments are releasing their geographic data to the public, and collaborative platforms are producing impressive amounts of cartography. With such an overwhelming amount of information, it is of paramount importance to develop smart systems that are able to handle and analyze these data. The scalability of deep learning and its ability to gain insight from large-scale datasets, makes it particularly interesting to the remote sensing community. It is often the case, however, that the deep learning advances in other domains cannot be directly applied to remote sensing. The type of input data and the constraints of remote sensing problems require the design of specific deep learning techniques. In this talk, I will discuss how deep learning approaches help in remote sensing image interpretation. In particular, I will focus on the most powerful architectures for semantic labeling of aerial and satellite optical images, with the final purpose to produce and update world maps. Papers: - N. Girard, G. Charpiat, Y. Tarabalka, "Aligning and updating cadaster maps with aerial images by multi-resolution, multi-task deep learning", ACCV 2018. - A. Zampieri, G. Charpiat, N. Girard and Y. Tarabalka, "Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing", ECCV, Munich, Germany, 2018. - B. Huang, K. Lu, N. Audebert, A. Khalel, Y. Tarabalka, J. Malof, A. Boulch, B. Le Saux, L. Collins, K. Bradbury, S. Lefèvre and M. El-Saban, "Large-scale semantic classification: outcome of the first year of Inria aerial image labeling benchmark", IGARSS'18, Valencia, Spain, 2018. - N. Girard and Y. Tarabalka, "End-to-End Learning of Polygons for Remote Sensing Image Classification", IGARSS'18, Valencia, Spain, 2018.

Learning Center - Campus Sophia Polytech

Route des Colles · Sophia-Antipolis

    Meetups précédents (15)

    À propos de ce groupe

    If you are interested in Data Science - be it applied or theoretical - don't hesitate to join us! You are most welcome. We are prepared to talk about every possible topic in Data Science: machine learning, deep learning, high-dimensional (and low-dimensional) computer age statistical inference, data base management, algorithms, computing/ software, communication/data visualization, etc. Obviously, the corresponding methods can be used to make sense of data in a wide range of fields - medicine, biology, finance, genomics, proteomics, image/sound recognition, webmining, internet of things, NLP/textmining, sensors, marketing analytics, astronomy, ... you name it - and you should be prepared to have the opportunity to listen to talks about all of these and more.

    Si vous êtes intéressé(e) par la Data Science - qu'elle soit appliquée ou théorique - n'hésitez pas à nous joindre. Vous êtes bienvenu(e). Nous avons des présentations sur tous les sujets possibles de la Data Science: l'apprentissage machine, l'apprentissage profond, la statistique de dimension élevée (ou réduite), les algorithmes, la programmation, les logiciels, la gestion de base de données, communication/ visualisation de données, etc.. Bien évidemment, les méthodes correspondantes peuvent être utilisées dans des domaines les plus divers - médecine, biologie, finance, génomique, protéomique, reconnaissance d'image/de son, webmining, internet of things, NLP/textmining, senseur, marketing, astronomie, etc - et vous allez avoir l'opportunité d'assister à des présentations sur tous ces sujets et bien d'autres.

    Membres (542)

    Photos (1)