Guillaume Astruc
@g_astruc
Followers
68
Following
157
Media
12
Statuses
36
2nd Year PhD Student from Imagine-ENPC/IGN/CNES
Joined July 2022
🤔 What if embedding multimodal EO data was as easy as using a ResNet on images?.Introducing AnySat: one model for any resolution (0.2m–250m), scale (0.3–2600 hectares), and modalities (choose from 11 sensors & time series)!.Try it with just a few lines of code:
2
9
43
RT @nico_dufour: I will be at #CVPR2025 this week in Nashville. I will be presenting our paper "Around the World in 80 Timesteps:.A Genera….
0
5
0
RT @RyanBoustany_: 📢New preprint.“When majority rules, minority loses: bias amplification of gradient descent”. We often blame biased data….
arxiv.org
Despite growing empirical evidence of bias amplification in machine learning, its theoretical foundations remain poorly understood. We develop a formal framework for majority-minority learning...
0
2
0
We've added new experiments demonstrating robust generalization capabilities! Notably, AnySat shows strong performance on HLS Burn Scars - a sensor never seen during pretraining! 🔥🛰️.Check it out: .📄 Paper: 🌐 Project:
AnySat has been accepted as a ✨highlight at #CVPR2025! 🎉 See you in Nashville!. We'll also be presenting this work at:. 📍 @EuroGeosciences on 02/04 in Vienna. 📍 @esa /@NASA Workshop on Foundation Models on 05/04 in Rome.
0
1
9
RT @Lucas__Ventura: Introducing Chapter-Llama [#CVPR2025], a framework for 𝐯𝐢𝐝𝐞𝐨 𝐜𝐡𝐚𝐩𝐭𝐞𝐫𝐢𝐧𝐠 using Large Language Models! 🎬🦙. Check it out:….
0
38
0
RT @antoine_guedon: 💻We've released the code for our #CVPR2025 paper MAtCha!. 🍵MAtCha reconstructs sharp, accurate and scalable meshes of b….
0
82
0
RT @thibaut_loiseau: 1/13 🐊 Introducing our latest work on improving relative camera pose regression with a novel pre-training approach All….
0
8
0
RT @thibaut_loiseau: 🧩Excited to share our paper "RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges" https://t.c….
0
4
0
RT @NayelBettache: 🎉 Excited to share my first single-author preprint. Proud of this contribution. I would be grateful for any feedback or….
0
2
0
🔗 Check it out:.📜 Paper: 🌐 Project: 🤗 HuggingFace: 🐙 GitHub:
1
0
7
🚀 Even better: AnySat supports linear probing for semantic segmentation!.That means you can fine-tune just a few thousand parameters and achieve SOTA results on challenging tasks—all with minimal effort.
1
0
5
AnySat achieves SOTA performance on 6 tasks across 10 datasets:.🌱 Land cover mapping.🌾 Crop type segmentation.🌳 Tree species classification.🌊 Flood detection.🌍 Change detection
1
0
5
We trained AnySat on 5 multimodal datasets simultaneously:.📡 11 distinct sensors.📏 Resolutions: 0.2m–500m.🔁 Revisit: single date to weekly.🏞️ Scales: 0.3–150 hectares.The pretrained model can adapt to truly diverse data, and probably yours too!
1
0
6
🔍Thanks to our modified JEPA training scheme and scale-adaptive spatial encoders, AnySat trains on datasets with diverse scales, resolutions, and modalities!.🧠 75% of its parameters are shared across all inputs, enabling unmatched flexibility.
1
0
5
RT @robmarkcole: AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities.
0
6
0
RT @isaaccorley_: AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities. @g_astruc @NicaoGr Clement Mallet @loicla….
0
9
0
RT @antoine_guedon: ⚠️Reconstructing sharp 3D meshes from a few unposed images is a hard and ambiguous problem. ☑️With MAtCha, we leverage….
0
40
0
RT @nico_dufour: 🌍 Guessing where an image was taken is a hard, and often ambiguous problem. Introducing diffusion-based geolocation—we pre….
0
37
0
RT @RyanBoustany_: 🚀 Excited to share our new preprint with @jerome_bolte, E. Pauwels & A. Purica: "A second-order-like optimizer with adap….
0
6
0