Recent publications include:
2023
Artificial intelligence to advance Earth observation: a perspective, Devis Tuia, Konrad Schindler, Begüm Demir, Gustau Camps-Valls, Xiao Xiang Zhu, Mrinalini Kochupillai, Sašo Džeroski, Jan N. van Rijn, Holger H. Hoos, Fabio Del Frate, Mihai Datcu, Jorge-Arnulfo Quiané-Ruiz, Volker Markl, Bertrand Le Saux, Rochelle Schneider, arXiv:2305.08413, May 2023.
2022 ECMWF-ESA workshop report: current status, progress and opportunities in machine learning for Earth system observation and prediction, Rochelle Schneider, Massimo Bonavita, Rossella Arcucci, Matthew Chantry, Marcin Chrust, Alan Geer, Bertrand Le Saux, and Claudia Vitolo, npj Climate and Atmospheric Science, to appear 2023.
[ to appear ]
Knowledge distillation for memory-efficient on-board image classification of Mars imagery, Piotr Bosowski, Nicolas Longépé, Bertrand Le Saux, Jakub Nalepa, IGARSS 2023, July 2023, Pasadena, CA, USA.
[ IEEE pdf later / IGARSS info later ]
Unbiased validation of hyperspectral unmixing algorithms, Lukasz Tulczyjew, Michal Kawulok, Nicolas Longépé, Bertrand Le Saux, Jakub Nalepa, IGARSS 2023, July 2023, Pasadena, CA, USA.
[ IEEE pdf later / IGARSS info later ]
Cloud detection in multispectral satellite images using support vector machines with quantum kernels, Artur Miroszewski, Jakub Mielczarek, Filip Szczepanek, Grzegorz Czelusta, Bartosz Grabowski, Bertrand Le Saux, Jakub Nalepa, IGARSS 2023, July 2023, Pasadena, CA, USA.
[ IEEE pdf later / IGARSS info later ]
Optimizing Kernel-Target Alignment for cloud detection in multispectral satellite images, Artur Miroszewski, Jakub Mielczarek, Filip Szczepanek, Grzegorz Czelusta, Bartosz Grabowski, Bertrand Le Saux, Jakub Nalepa, IGARSS 2023, July 2023, Pasadena, CA, USA.
[ IEEE pdf later / IGARSS info later ]
Analysing the impact of PQK Transform on the multispectral features, Manish K. Gupta, Michał Romaszewski, Bertrand Le Saux, Piotr Gawron, IGARSS 2023, July 2023, Pasadena, CA, USA.
[ IEEE pdf later / IGARSS info later ]
Detecting Clouds in Multispectral Satellite Images Using Quantum-Kernel Support Vector Machines Artur Miroszewski, Jakub Mielczarek, Grzegorz Czelusta, Filip Szczepanek, Bartosz Grabowski, Bertrand Le Saux, Jakub Nalepa, to appear, pre-print available.
A Single-Step Multiclass SVM based on Quantum Annealing for Remote Sensing Data Classification Amer Delilbasic, Bertrand Le Saux, Morris Riedel, Kristel Michielsen, Gabriele Cavallaro, to appear, pre-print available.
Towards generation of synthetic hyperspectral image datasets with GAN, François De Vieilleville, Adrien Lagrange, Nicolas Dublé, and Bertrand Le Saux, EGU’2023, Vienna, Austria, April 2023.
[ EGU abstract ]
Confidence estimation of DNN predictions for on-board applications, Nicolas Dublé, François De Vieilleville, Adrien Lagrange, and Bertrand Le Saux, EGU’2023, Vienna, Austria, April 2023.
[ EGU abstract / doi ]
Correlation between PQC Descriptors and Training Accuracy in Hybrid Quantum-Classical Model for Earth Observation Image Classification, Su-yeon Chang, B. Le Saux, S. Vallecorsa, M. Grossi, Quantum Information Processing (QIP 2023), Ghent, Belgium, February 2023.
[ QIP website ]
Multispectral Satellite Data Analysis Using Support Vector Machines With Quantum Kernels, Artur Miroszewski, F. Szczepanek, G. Czelusta, B. Grabowski, B. Le Saux, J. Nalepa and J. Mielczarek, Quantum Information Processing (QIP 2023), Ghent, Belgium, February 2023.
[ QIP website ]
2022
Report on the 2022 IEEE Geoscience and Remote Sensing Society Data Fusion Contest: Semisupervised Learning Hänsch, R.; Persello, C.; Vivone, G.; Castillo Navarro, J.; Boulch, A.; Lefèvre, S.; Le Saux, B., IEEE Geoscience and Remote Sensing Magazine, vol. 10, no. 4, pp. 270-273, Dec. 2022, doi: 10.1109/MGRS.2022.3219935.
[ IEEE GRSM version / doi / DFC 2022 benchmark / data ]
Rapid Training of Quantum Recurrent Neural Networks, M. Siemaszko, T. McDermott, A. Buraczewski, B. Le Saux and M. Stobińska, QTML’2022, Naples, Italy, Nov 2022.
[ arxiv ]
The Hyperview Challenge: Estimating Soil Parameters from Hyperspectral Images Jakub Nalepa, Bertrand Le Saux, Nicolas Longépé, Lukasz Tulczyjew, Michal Myller, Michal Kawulok, Krzysztof Smykala, Michal Gumiela, ICIP 2022, Bordeaux, France, October 2022.
[ editor version / doi / challenge ]
Learning Local Depth Regression from Defocus Blur by Soft-Assignment Encoding, R. Leroy, P. Trouvé, B. Le Saux, B. Buat, F. Champagnat, Optica Applied Optics, October 2022.
[ Appl. Opt. / pdf ]
Hybrid Quantum-Classical Networks for Reconstruction and Classification of Earth Observation Images, Su-yeon Chang, S. Vallecorsa, M. Grossi, B. Le Saux, 21st Int. Ws on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2022), Bari, Italy, October 2022.
[ ]
Multiclass SVM with Quantum Annealing, A. Delilbasic, G. Cavallaro, B. Le Saux, M. Riedel and K. Michielsen, Quantum Machine Learning workshop at ECML-PKDD 2022, Grenoble, France, Sep 2022.
Rapid Training of Quantum Recurrent Neural Network, M. Siemaszko, T. McDermott, A. Buraczewski, B. Le Saux and M. Stobińska, Quantum Machine Learning workshop at ECML-PKDD 2022, Grenoble, France, Sep 2022.
Language Transformers for Remote Sensing Visual Question Answering, C. Chappuis, V. Mendez, E. Walt, D. Tuia, S. Lobry, B. Le Saux, IGARSS 2022, July 2022.
[ IEEE pdf / IGARSS info ]
Weakly-supervised Continual Learning for Class-Incremental Segmentation, G. Lenczner, A. Chan-Hon-Tong, N. Luminari, B. Le Saux, IGARSS 2022, July 2022.
[ IEEE pdf / arxiv / IGARSS info / code ]
Quantum Convolutional Circuits for Earth Observation Image Classification, Su-yeon Chang, S. Vallecorsa, M. Grossi, B. Le Saux, IGARSS 2022, July 2022.
[ IEEE pdf / IGARSS info ]
ESA-ECMWF Report on recent progress and research directions in machine learning for Earth System observation and prediction, R. Schneider, M. Bonavita, A. Geer, R. Arcucci, P. Dueben, C. Vitolo, B. Le Saux, B. Demir & PP. Mathieu, npj climate and atmospheric science 5 (51), June 2022.
[ NPJ CAS version / doi / workshop website ml4esop.esa.int ]
A Multibranch Convolutional Neural Network for Hyperspectral Unmixing Lukasz Tulczyjew, Michal Kawulok, Nicolas Longépé, Bertrand Le Saux, Jakub Nalepa, IEEE Geoscience and Remote Sensing Letters (GRSL), June 2022.
[ editor version / arxiv ]
Graph Neural Networks Extract High-Resolution Cultivated Land Maps From Sentinel-2 Image Series Lukasz Tulczyjew, Michal Kawulok, Nicolas Longépé, Bertrand Le Saux, Jakub Nalepa, IEEE Geoscience and Remote Sensing Letters (GRSL), June 2022.
[ editor version / arxiv ]
Self-supervised learning – A way to minimize time and effort for precision agriculture? M. Marszalek, B. Le Saux, PP Mathieu, A. Nowakowski, D. Springer, ISPRS Congress 2022, June 2022.
Prompt-RSVQA: Prompting Visual Context to a Language Model for Remote Sensing Visual Question Answering C. Chappuis, V. Zermatten, S. Lobry, B. Le Saux, D. Tuia, CVPR 2022 / Earth Vision workshop, June 2022.
[ CVF page with abstract / CVPR/EV22 pdf / arxiv to appear ]
2022 IEEE GRSS Data Fusion Contest: Semi-Supervised Learning Hänsch, R.; Persello, C.; Vivone, G.; Castillo Navarro, J.; Boulch, A.; Lefèvre, S.; Le Saux, B., IEEE Geoscience and Remote Sensing Magazine (GRSM), March 2022.
[ editor version / DFC 2022 benchmark / data ]
DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensing G. Lenczner, A. Chan-Hon-Tong, B. Le Saux, N. Luminari, G. Le Besnerais, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), March 2022.
[ editor version / arxiv / DIAL code ]
Deep Learning for Archaeological Object Detection on LiDAR: New Evaluation Measures and Insights Marco Fiorucci, Wouter B. Verschoof-van der Vaart, Paolo Soleni, Bertrand Le Saux and Arianna Traviglia, Remote Sensing, March 2022.
[ Open-access editor version ]
2021
Quantum Machine Learning for Earth Observation Images, Su-yeon Chang, S. Vallecorsa, B. Le Saux, NeurIPS 2nd WS on Quantum Tensor Networks in Machine Learning, Dec. 2021.
[ abstract ]
Energy-based Models in Earth Observation: from Generation to Semi-supervised Learning J. Castillo-Navarro, B. Le Saux, A. Boulch, S. Lefèbre, IEEE Trans. on Geosciences and Remote Sensing (TGRS), November 2021.
[ TGRS pdf / doi / arxiv (to appear) / hal ]
CORTEX: An innovative solution for AI on-board, R. Ruiloba, A. Lagrange, N.-M. Lemoine, F. De Vieilleville, B. Le Saux, European CubeSat Symposium, Nov. 2021
[ pdf (to appear) / Project page / Sentinel 2 Ship detection dataset ]
On Circuit-based Hybrid Quantum Neural Networks for Remote Sensing Imagery Classification, A. Sebastianelli, D. A. Zaidenberg, D. Spiller, B. Le Saux, S. L. Ullo, IEEE JSTARS, 15, Sep. 2021
[ JSTARS pdf / arxiv / arxiv pdf / code ]
How to find a good image-text embedding for remote sensing visual question answering? C. Chappuis, S. Lobry, B. Kellenberger, B. Le Saux, D. Tuia, ECML-PKDD 2021 / MACLEAN workshop, Sept. 2021.
[ CEUR Proceedings / CEUR pdf / arxiv / arxiv pdf / video ]
Deep Learning‐based Semantic Segmentation in Remote Sensing D. Tuia, D. Marcos, K. Schindler, B. Le Saux chapter of: Deep learning for the Earth Sciences G. Camps-Valls, D. Tuia, XX Zhu, M. Reichstein (ed), Wiley, 2021
[ doi ]
Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport R. Leroy, P. Trouvé, F. Champagnat, B. Le Saux, M. Carvalho, MVA 2021, August 2021.
[ MVA’21 pdf / arxiv / arxiv pdf ]
Advantages and Bottlenecks of Quantum Machine Learning for Remote Sensing D. Zaidenberg, A. Sebastianelli, D. Spiller, B. Le Saux, S. L. Ullo, IGARSS 2021, July 2021.
[ IEEE pdf / arxiv / arxiv pdf / IGARSS info ]
Classification and Generation of Earth-observation Images using a Joint Energy-based Model J. Castillo-Navarro, B. Le Saux, A. Boulch, S. Lefèbre, IGARSS 2021, July 2021.
[ IEEE pdf / IGARSS info ]
Long-term Burned Area Reconstruction through Deep Learning S. Lampe, B. Le Saux, I. Vanderkelen, W. Thiery, ICML 2021 / Climate Change AI workshop, July 2021.
Weakly supervised change detection using guided anisotropic diffusion R. Caye , B. Le Saux, A. Boulch, Y. Gousseau, Maching Learning Journal, June 2021.
[ editor version / doi / arxiv ]
Energy-based Models for Earth Observation Applications J. Castillo-Navarro, B. Le Saux, A. Boulch, S. Lefèbre, ICLR 2021 / Energy-based Model workshop, April 2021.
Machine learning for Earth system observation and prediction M. Bonavita, R. Arcucci, A. Carrassi, P. Dueben, A. J Geer, B. Le Saux, N. Longépé, P.-P. Mathieu, L. Raynaud, Bulletin of the American Meteorological Society (BAMS) 102 (4) April 2021.
[ article / doi / ECMWF-ESA Workshop on Machine Learning for Earth System Observation and Prediction (ML4ESOP) ]
Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study J. Castillo-Navarro, B. Le Saux, A. Boulch, N. Audebert, S. Lefèbre, Maching Learning Journal, April 2021.
[ editor version / doi / local file / arxiv / hal / MiniFrance dataset ]
2020
Street to Cloud: Improving Flood Maps With Crowdsourcing and Semantic Segmentation V. Sunkara, M. Purri, B. Le Saux, J. Adams, NeurIPS 2020 Workshop on Climate Change AI, virtual, December 2020
[ CCAI page with video / arxiv ]
Large-Scale Semantic 3-D Reconstruction: Outcome of the 2019 IEEE GRSS Data Fusion Contest - Part B Yanchao Lian, Tuo Feng, Jinliu Zhou, Meixia Jia, Aijin Li, Zhaoyang Wu, Licheng Jiao, M. Brown, G. Hager, N. Yokoya, R. Hänsch, B. Le Saux IEEE JSTARS, 14, 1158-1170 November 2020
[ doi (open access) / DFC2019 / Dataset on dataport ]
Large-Scale Semantic 3-D Reconstruction: Outcome of the 2019 IEEE GRSS Data Fusion Contest - Part A H. Chen, M. Lin, H. Zhang, P. D’Angelo, D. Cerra, S. M. Azimi, M. Brown, G. Hager, N. Yokoya, R. Hänsch, B. Le Saux IEEE JSTARS, 12, 922-935 October 2020
[ doi (open access) / DFC2019 / Dataset on dataport ]
Interactive Learning for Semantic Segmentation in Earth Observation G. Lenczner, B. Le Saux, N. Luminari, A. Chan-Hon-Tong, G. Le Besnerais, ECML/PKDD MACLEAN, Virtual / Ghent, Belgium, September 2020
[ Best Student Paper Award / local pdf / CEUR Proc. / ext pdf / DISIR/DISCA video / DISCA code ]
On Auxiliary Losses for Semi-Supervised Semantic Segmentation J. Castillo-Navarro, B. Le Saux, A. Boulch, S. Lefèbre, ECML/PKDD MACLEAN, Virtual / Ghent, Belgium, September 2020
[ local pdf / CEUR Proc. / ext pdf / video ]
DISIR: Deep image segmentation with interactive refinement G. Lenczner, B. Le Saux, N. Luminari, A. Chan-Hon-Tong, G. Le Besnerais, ISPRS Annals, Virtual / Nice, France, August 2020
[ local pdf / ISPRS ann. / ISPRS video / arxiv / DISIR code ]
Flood detection in times series of optical and SAR images C. Rambour, N. Audebert, É. Koeniguer, B. Le Saux, M. Crucianu, M. Datcu, ISPRS Archives, Virtual / Bice, France, August 2020
[ local pdf / ISPRS arch. / hal / SEN12-FLOOD dataset ]
A real-world hyperspectral imaging processing workflow for vegetation stress and hydrocarbon indirect detection D. Dubucq, N. Audebert, V. Achard, S. Fabre, A. Credoz, Ph. Deliot, B. Le Saux, ISPRS Archives, Virtual / Nice, France, August 2020
[ local pdf / ISPRS arch. / hal ]
Segmentation sémantique d’images aériennes avec améliorations interactivesG. Lenczner, B. Le Saux, N. Luminari, A. Chan-Hon-Tong, G. Le Besnerais, RFIAP, Virtual / Vannes, France, June 2020
Pix2Point : prédiction monoculaire de scènes 3D par réseaux de neurones hybrides et transport optimal, Rémy Leroy, Bertrand Le Saux, Marcela Carvalho, Pauline Trouvé-Peloux, and Frédéric Champagnat, RFIAP, Virtual / Vannes, France, June 2020
[ pdf ]
2019
Machine Learning Models for Scene Understanding Bertrand Le Saux, Habilitation Thesis (HDR, University of Paris-Saclay), December 2019
2019 IEEE GRSS Data Fusion Contest: Large-Scale Semantic 3D Reconstruction B. Le Saux, N. Yokoya, R. Hänsch, M. Brown, G. Hager, Geoscience and Remote Sensing Magazine (GRSM), December 2019
[ doi / Open-Access pdf / DFC 2019 website ]
Multitask learning of Height and Semantics From Aerial Images M. Pinheiro de Carvalho, B. Le Saux, P. Trouvé-Peloux, F. Champagnat, A. Almansa Geoscience and Remote Sensing Letters (GRSL), Nov. 2019
[ doi / hal / pdf #1 / code on github ]
Distance transform regression for spatially-aware deep semantic segmentation N. Audebert, A. Boulch, B. Le Saux, S. Lefèvre, Computer Vision and Image Understanding (CVIU), vol. 189, Dec. 2019
Multitask learning for large-scale semantic change detection R. Caye Daudt, B. Le Saux, A. Boulch, Y. Gousseau Computer Vision and Image Understanding (CVIU), vol. 187, Oct. 2019
[ doi / arxiv / pdf / HRSCD dataset ]
Réseaux de neurones semi-supervisés pour la segmentation sémantique en télédétection J. Castillo Navarro, B. Le Saux, A. Boulch, S. Lefèvre Colloque GRETSI, Lille, France, Sept. 2019
Learning to understand Earth-observation images with weak and unreliable ground-truth R. Caye Daudt, A. Chan-Hon-Tong, B. Le Saux, A. Boulch IGARSS 2019, Yokohama, Japan, July 2019
[ ieee https://doi.org/10.1109/IGARSS.2019.8898563 ]
Deep Learning for Classification of Hyperspectral Data: A Comparative Review N. Audebert, B. Le Saux, S. Lefèvre IEEE Geoscience and Remote Sensing Magazine, vol. 7 (2), June 2019
[ doi / arxiv / hal / DeepHyperX toolbox ]
Advanced Multi-Sensor Optical Remote Sensing for Urban Land Use and Land Cover Classification: Outcome of the 2018 IEEE GRSS Data Fusion Contest Y. Xu, B. Du, L. Zhang, D. Cerra, M. Pato, E. Carmona, S. Prasad, N. Yokoya, R. Hänsch, B. Le Saux IEEE JSTARS, June 2019
[ doi (open access) / DFC2018 ]
Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection R. Caye Daudt, B. Le Saux, A. Boulch, Y. Gousseau IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR / EarthVision 19) Long Beach, Cal., USA, June 2019
[ Best Student Paper Award pdf#1 / pdf#2 / arxiv ]
What data do we need for semantic segmentation in Earth-observation? J. Castillo Navarro, N. Audebert, A. Boulch, B. Le Saux, S. Lefèvre IEEE Joint Urban Remote Sensing Event (JURSE’2019) Vannes, France, May 2019
2019 IEEE GRSS Data Fusion Contest: Large-Scale Semantic 3D Reconstruction B. Le Saux, N. Yokoya, R. Hänsch, M. Brown, G. Hager, Geoscience and Remote Sensing Magazine (GRSM), March 2019
[ doi / Open-Access pdf / DFC 2019 website ]
2018
Fully Convolutional Siamese Networks for Change Detection R. Caye Daudt, B. Le Saux, A. Boulch IEEE Int. Conf. on Image Processing (ICIP’2018) Athens, Greece, October 2018
On Regression Losses for Deep Depth Estimation M. Pinheiro de Carvalho, B. Le Saux, P. Trouvé-Peloux, F. Champagnat, A. Almansa IEEE Int. Conf. on Image Processing (ICIP’2018) Athens, Greece, October 2018
[ pdf / hal / D3-Net code ]
Deep Depth from Defocus: how can defocus blur improve 3D estimation using dense neural networks? M. Pinheiro de Carvalho, B. Le Saux, P. Trouvé-Peloux, F. Champagnat, A. Almansa IEEE Eur. Conf. on Computer Vision (ECCV’2018) / Workshop on 3D Reconstruction in the Wild Munich, Germany, September 2018
[ arxiv / pdf / pdf #2 / code and dataset ]
Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks R. Caye Daudt, B. Le Saux, A. Boulch, Y. Gousseau IEEE International Geoscience and Remote Sensing Symposium (IGARSS’2018) Valencia, Spain, July 2018
[ pdf ]
Generative adversarial networks for realistic synthesis of hyperspectral samples N. Audebert, B. Le Saux, S. Lefèvre IEEE International Geoscience and Remote Sensing Symposium (IGARSS’2018) Valencia, Spain, July 2018
Railway Detection: from filtering to segmentation networks B. Le Saux, A. Beaupère, A. Boulch, J. Brossard, A. Manier, G. Villemin IEEE International Geoscience and Remote Sensing Symposium (IGARSS’2018) Valencia, Spain, July 2018
[ pdf ]
Learning speckle suppression in SAR images without ground truth: application to Sentinel-1 time-series A. Boulch, P. Trouvé, É. Koeniguer, F. Janez, B. Le Saux IEEE International Geoscience and Remote Sensing Symposium (IGARSS’2018) Valencia, Spain, July 2018
[ pdf ]
Large-scale semantic classification: outcome of the first year of INRIA Aerial Image Labeling Benchmark B.H. Huang, K.K. Lu, N. Audebert, A. Khalel, Y. Tarabalka, J. Malof, A. Boulch, B. Le Saux, L. Collins, K. Bradbury, S. Lefèvre, M. El-Saban IEEE International Geoscience and Remote Sensing Symposium (IGARSS’2018) Valencia, Spain, July 2018
Estimation de profondeur monoculaire par réseau de neurones et l’apport du flou de défocalisation M. Pinheiro de Carvalho, B. Le Saux, P. Trouvé-Peloux, F. Champagnat, A. Almansa Congrès Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP’2018) Marne-la-Vallée, France, July 2018
[ Best Paper Award pdf #1 / pdf #2 / hal ]
Détection dense de changements par réseaux de neurones siamois R. Caye Daudt, B. Le Saux, A. Boulch, Y. Gousseau Congrès Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP’2018) Marne-la-Vallée, France, July 2018
[ Rodrigo’s site pdf ]
Segmentation sémantique profonde par régression sur cartes de distances signées N. Audebert, A. Boulch, B. Le Saux, S. Lefèvre Congrès Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP’2018) Marne-la-Vallée, France, July 2018
Open data for global multimodal land use classification: Outcome of the 2017 IEEE GRSS Data Fusion Contest N. Yokoya, P. Ghamisi, J. Xia, S. Sukhanov, R. Heremans, C. Debes, B. Bechtel, B. Le Saux, G. Moser, D. Tuia, IEEE JSTARS, 2018
Beyond RGB: Very high resolution urban remote sensing with multimodal deep networks Nicolas Audebert, Bertrand Le Saux, Sébastien Lefèvre, ISPRS Journal of Photogrammetry and Remote Sensing, 2018