Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 14/08/2026Co-learning can be boosted to handle missing modalities in multi-modal classification! We present our latest findings in this work accepted at the Discovery Science conference 021
Francisco Mena @fmenat.bsky.social · 14/08/2026Co-learning can be boosted to handle missing modalities in multi-modal classification! We present our latest findings in this work accepted at the Discovery Science conference 021
Reposted by Francisco Menaarxiv cs.CV @arxiv-cs-cv.bsky.social · 23/10/2025Francisco Mena, Dino Ienco, Cassio F. Dantas, Roberto Interdonato, Andreas Dengel Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration arxiv.org/abs/2510.19579 011
Reposted by Francisco MenaarXiv cs.CV Computer Vision and Pattern Recognition @cscv-bot.bsky.social · 23/10/2025Francisco Mena, Dino Ienco, Cassio F. Dantas, Roberto Interdonato, Andreas Dengel: Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration arxiv.org/abs/2510.19579 arxiv.org/pdf/2510.19579 arxiv.org/html/2510.19579 013
Francisco Mena @fmenat.bsky.social · 11/06/2026A crop yield prediction dataset 🌱 at sub-field level (10 m) with data from Germany, Argentina and Uruguay 🌎. 010
Reposted by Francisco MenaarXiv cs.LG Machine Learning @cslg-bot.bsky.social · 10/04/2025Miro Miranda, Francisco Mena, Andreas Dengel: An Analysis of Temporal Dropout in Earth Observation Time Series for Regression Tasks arxiv.org/abs/2504.06915 arxiv.org/pdf/2504.06915 arxiv.org/html/2504.06915 113
Reposted by Francisco MenaFabian Theis @fabiantheis.bsky.social · 09/06/2026Excited to kick off #HAICON26 today! 🚀🤖 More than 600 participants joining us to explore how AI is transforming science and accelerating discovery. Great energy, great people, and an exciting program ahead. 👉 haicon.cc #AIforScience #HAICON26 041
Reposted by Francisco MenaHelmholtz Imaging @helmholtzimaging.bsky.social · 09/06/2026Looking for the #HelmholtzImaging team at #HAICON26? You'll find us at our booth today & throughout the conference. Come by to learn about our tools, resources, projects & training opportunities for @helmholtz.de researchers. And grab a scientific image poster while supplies last! 👀 See you! 👋 063
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 11/05/2026I'm quite happy to share that after submitting my PhD in September last year, I finally defended my PhD at @rptu.bsky.social 😁😁. It was a long journey in @dfki.bsky.social filled with experiences and learning 🤖 141
Francisco Mena @fmenat.bsky.social · 11/05/2026I'm quite happy to share that after submitting my PhD in September last year, I finally defended my PhD at @rptu.bsky.social 😁😁. It was a long journey in @dfki.bsky.social filled with experiences and learning 🤖 141
Reposted by Francisco MenaIAPR Technical Committee 7 (TC7) – Earth Observation @iaprtc7.bsky.social · 23/04/2026Do not miss the deadline for the PRRS workshop at ICPR 2026 in Lyon, France: May 5th! More info: iapr-tc7.github.io/prrs2026/iapr-tc7.github.io14th IAPR Workshop on Pattern Recognition in Remote SensingTechnical Committee 7 on Earth Observation of the International Association for Pattern Recognition 012
Reposted by Francisco MenaECMWF @ecmwf.int · 25/02/2026📣 Applications are open for ECMWF’s Code for Earth 2026! New data driven challenges across visualisation, machine learning, software development plus a brand new Africa focused stream with African partners. 📅 Apply by 9 April 2026 @codeforearth.bsky.social www.ecmwf.int/en/about/med... 085
Reposted by Francisco MenaBIFOLD Berlin Institute for the Foundations of Learning and Data @bifold.berlin · 19/01/2026🎓 10 #PhD positions in #AI & #DataScience - #Berlin BIFOLD is hiring 10 PhD candidates in: 🤖 #MachineLearning 🗄️ #DataManagement 🔗 #ML × #DM Apply until Feb 13, 2026 www.jobs.tu-berlin.de/en/job-posti... @tuberlin.bsky.social @rieck.mlsec.org #AcademicSky #PhDSky #sciencejobs #academicjobs 173
Francisco Mena @fmenat.bsky.social · 02/12/2025I'm traveling 🚄 towards Copenhagen 🇩🇰 for #Eurips. Happy to catch up if you are around 😀 030
Francisco Mena @fmenat.bsky.social · 21/11/2025We combine contrastive learning + modality-discriminative losses to structure features into shared and specific subspaces. Tested on four EO benchmarks (classification & regression) → consistent gains over both EO and ML state-of-the-art. 000
Francisco Mena @fmenat.bsky.social · 21/11/2025I'm happy to share that our new paper in Multi-modal co-learning for Earth observation got published in the ML journal🌍📡 Here, we show how models trained on multiple sensor modalities can boost single-modality inference 🔗 link.springer.com/article/10.1...link.springer.comMulti-modal co-learning for Earth observation: enhancing single-modality models via modality collaboration - Machine LearningMulti-modal co-learning is emerging as an effective paradigm in machine learning, enabling models to collaboratively learn from different modalities to enhance single-modality predictions. Earth Obser... 130
Reposted by Francisco MenaNature @nature.com · 26/10/2025We asked 3,785 PhD students across 107 countries about their experiences. Where do you think the happiest doctoral candidates were? go.nature.com/43usVmfgo.nature.comAre these the happiest PhD students in the world?Nature - Brazil, Australia and Italy have the highest satisfaction scores in Nature’s global 2025 PhD survey — but are these nations really the best places to do a doctorate? 03611
Reposted by Francisco MenaClimate AI Nordics @climateainordics.com · 19/09/2025🌍 Excited to announce our Workshop on AI for Climate & Conservation (AICC) at #EurIPS2025 in Copenhagen! 🎉 📢 Call for Participation: sites.google.com/g.harvard.ed... Confirmed speakers from Mistral AI, DeepMind, ETH Zurich, LSCE & more. Looking forward to meeting and discussing in Copenhagen! 12010
Reposted by Francisco MenaNico Lang @nicolang.bsky.social · 09/10/2025Working on representation learning for Earth Observation? Come join the discussion at the EurIPS workshop "REO: Advances in Representation Learning for Earth Observation" Call for papers deadline: October 15, AoE Workshop site: sites.google.com/view/reoeurips @euripsconf.bsky.social @esa.int 084
Francisco Mena @fmenat.bsky.social · 24/09/2025Always happy to receive those accepted paper email 😃 010
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 11/09/2025It is possible to reduce the number of experiments when searching for the best combination of encoder architecture and fusion strategy for crop classification 🌱🚜? Spoiler alert: In our recent (open access) paper 📖, we show that it can! www.sciencedirect.com/science/arti...sciencedirect.comIn the search for optimal multi-view learning models for crop classification with global remote sensing dataStudying and analyzing cropland is a difficult task due to its dynamic and heterogeneous growth behavior. Usually, diverse data sources can be collect… 121
Reposted by Francisco MenaNeurIPS Europe @neuripseurope.bsky.social · 12/09/2025We are delighted to announce the #EurIPS 2025 Workshops 🎉: eurips.cc/workshops/ We received 52 proposals, which were single-blind reviewed by more than 35 expert reviewers, leading to 18 accepted workshops (acceptance rate 34.6%).eurips.ccWorkshops - A NeurIPS-endorsed conference in EuropeA NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark 1175
Reposted by Francisco MenaDiego Marcos @dmarcosg.bsky.social · 08/09/2025We are looking for an NLP postdoc/engineer to work on adding language capabilities to our Earth observation sensor-agnostic models (Atomizer, to be presented at BMVC25). Details here: jobs.inria.fr/public/class... Atomizer: arxiv.org/pdf/2506.13542 GEO-ReSeT project: anr.fr/Projet-ANR-2... 032
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 13/05/2025Did you know that mutual distillation can be used to make deep learning models robust to missing sensor data? We present this in our recent paper from a collaboration between @dfki.bsky.social and Inria (evergreen team). Available at @ieeeaccess.bsky.social 🔓 ieeexplore.ieee.org/document/10994… 232
Francisco Mena @fmenat.bsky.social · 11/09/2025Considering the current substantial use of computational resources in deep learning research and its consequential impact on the carbon footprint 👣, it is important to look for systematic ways that lead us to reduce computational efforts 010
Francisco Mena @fmenat.bsky.social · 11/09/2025Instead of trying all possible combinations, the search could be reduced to a 2-step sequential search: 1) search for the best encoder architecture with early/input fusion, and then 2) with the encoder selected in (1), search for the best fusion strategy 110
Francisco Mena @fmenat.bsky.social · 11/09/2025When considering all the diverse encoder architectures (like convolutional or attention-based) and fusion strategies (like input and feature) from the literature, the search space of all possible model combinations is considerably big and a resource-wasting process. 100
Francisco Mena @fmenat.bsky.social · 11/09/2025It is possible to reduce the number of experiments when searching for the best combination of encoder architecture and fusion strategy for crop classification 🌱🚜? Spoiler alert: In our recent (open access) paper 📖, we show that it can! www.sciencedirect.com/science/arti...sciencedirect.comIn the search for optimal multi-view learning models for crop classification with global remote sensing dataStudying and analyzing cropland is a difficult task due to its dynamic and heterogeneous growth behavior. Usually, diverse data sources can be collect… 121
Reposted by Francisco Menaesaclimate @esaclimate.bsky.social · 27/08/2025🏞️ Today is @unep.org #WorldLakeDay! Global, long-term satellite records developed by the ESA Climate Change Initiative shed light on lakes contribution to the hydrological, energy and carbon cycles and their response to climate change. Check out the data set visualisations here: t1p.de/mvl0a 065
Reposted by Francisco MenaArno Solin @arnosolin.bsky.social · 12/08/2025📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS 2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. [1/3] 23721
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 01/08/2025Also, don't hesitate to visit our CCS in Probabilistic Machine Learning for Earth Observation (TU2.M1)! ⏲️ Tuesday, 5 August, 10:30 - 11:45 011
Francisco Mena @fmenat.bsky.social · 01/08/2025Also, don't hesitate to visit our CCS in Probabilistic Machine Learning for Earth Observation (TU2.M1)! ⏲️ Tuesday, 5 August, 10:30 - 11:45 011
Francisco Mena @fmenat.bsky.social · 01/08/2025⏲️ Thursday, 7 August, 15:45 - 17:00 📜 On What Depends the Robustness of Multi-source Models to Missing Data in Earth Observation? in the TH4.P11: Multi-source Semantic Segmentation (oral 🎤) ⭐I'll present our findings about three major factors that drive the robustness to missing data sources. 100
Francisco Mena @fmenat.bsky.social · 01/08/2025⏲️ Tuesday, 5 August, 09:15 - 10:30 📜 A Multi-modal Co-learning Model with Shared and Specific Features for Land-cover Classification in the TUP1.PB: Cross-Domain Learning and Semantic Segmentation in RS (poster🖼️) ⭐ Here we leverage co-learning and multiple losses to improve single-modality inference 120
Francisco Mena @fmenat.bsky.social · 01/08/2025This coming week will be a thrilling and enriching experience at IGARSS 2025. I'll be presenting two works in multi-modal/source learning focused on missing data sources. Let's catch up if you are around! #IGARSS #IEEE #GRSS #AI4EO #EO #AI 131
Reposted by Francisco MenaSebastian Bordt @sbordt.bsky.social · 10/07/2025During the last couple of years, we have read a lot of papers on explainability and often felt that something was fundamentally missing🤔 This led us to write a position paper (accepted at #ICML2025) that attempts to identify the problem and to propose a solution. arxiv.org/abs/2402.02870 👇🧵 1125
Francisco Mena @fmenat.bsky.social · 13/05/2025The code is available at github.com/fmenat/DSensDpgithub.comGitHub - fmenat/DSensDp: Public repository of our research work at IEEE AccessPublic repository of our research work at IEEE Access - fmenat/DSensDp 010
Francisco Mena @fmenat.bsky.social · 13/05/2025We show that our multi-sensor approach is more robust in average than recent methods from the EO literature in three classification tasks, namely cropland classification, crop-type classification, and tree-species classification. @interdonatos.bsky.social 031
Francisco Mena @fmenat.bsky.social · 13/05/2025Concretely, we use a mix of sensor dropout as data augmentation and mutual distillation to enhance collaborative learning across sensors, namely DSensD+. We leverage multi-task learning to combine various objectives to achieve an optimal robustness 100
Francisco Mena @fmenat.bsky.social · 13/05/2025Did you know that mutual distillation can be used to make deep learning models robust to missing sensor data? We present this in our recent paper from a collaboration between @dfki.bsky.social and Inria (evergreen team). Available at @ieeeaccess.bsky.social 🔓 ieeexplore.ieee.org/document/10994… 232
Reposted by Francisco MenaImagine-ENPC @imagineenpc.bsky.social · 30/04/2025#CVPR2025 Sat June 14 (PM) ✨ Highlight 🛰️ AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities @gastruc.bsky.social @nicaogr.bsky.social @loicland.bsky.social 📄 pdf: arxiv.org/abs/2412.14123 🌐 webpage: gastruc.github.io/anysat 1174
Reposted by Francisco MenaHelmholtz Imaging @helmholtzimaging.bsky.social · 30/04/2025ABSTRACT DEADLINE EXTENDED! Submit your talk or poster proposal for the 5th Helmholtz Imaging Conference by May 8. Join us June 25–27 in Potsdam & connect with the imaging community! Don’t miss it! 👉 bit.ly/HIConf25 #HIConference25 @www.helmholtz.de @dkfz.bsky.social @mdc-berlin.bsky.social 011
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 11/04/2025How will your multi-view model perform if data is missing during deployment? Usually, this translates into a considerable decline in accuracy. However, simpler approaches in model design can make it robust to missing data. We address this in our recent paper in the Neurocomputing journal. 131
Reposted by Francisco MenaELLIS @ellis.eu · 15/04/2025🔐 ✏️ Don't miss attending the ELLIS Summer School with @cispa.de & ELSA - European Lighthouse on Secure & Safe AI in Saarbrücken 🇩🇪 this August. Applications are open! 🔗 More details: elsa-ai.eu/save-the-dat... #ELLISPhDelsa-ai.euCISPA ELLIS Summer School 2025 – ELSA 042
Reposted by Francisco MenaFrancisco Mena @fmenat.bsky.social · 11/04/2025Our recent work, validated with heterogenous real-world data from the Earth observation domain, can be accessed (open-access 🔓) at the Neurocomputing journal www.sciencedirect.com/science/arti...sciencedirect.comMissing data as augmentation in the Earth Observation domain: A multi-view learning approachMulti-view learning (MVL) leverages multiple sources or views of data to enhance machine learning model performance and robustness. This approach has … 111
Francisco Mena @fmenat.bsky.social · 11/04/2025Our recent work, validated with heterogenous real-world data from the Earth observation domain, can be accessed (open-access 🔓) at the Neurocomputing journal www.sciencedirect.com/science/arti...sciencedirect.comMissing data as augmentation in the Earth Observation domain: A multi-view learning approachMulti-view learning (MVL) leverages multiple sources or views of data to enhance machine learning model performance and robustness. This approach has … 111
Francisco Mena @fmenat.bsky.social · 11/04/2025We show that simulating all possible Combinations of Missing (CoM) views during training allows the models to be aware of potential missing data during inference. This translates into a generalization to missing view scenarios (robustness increase) and improving regular performance in some cases 110