We evaluate the approach on 4 Earth observation datasets in both intra- and cross-dataset settings and compared it to other self supervised approaches and fondation models.
We also evaluate it in low data regime.

New version of the MAESTRO paper about self-supervised Learning for Earth Observation Data 🛰️✈️🗺️
arxiv.org/abs/2508.10894

We provide an intense benchmark of different ways to deal with multitemporal, multispectral, and multimodal data (fusion strategies / normalization schemes) for MAE based model.

I wil𝗹𝗹 𝗽𝗿𝗲𝘀𝗲𝗻𝘁: HySCDG, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation
🖼️ 𝗣𝗼𝘀𝘁𝗲𝗿 #187 Session 1,
This Friday, June 13 10:30 - 12:30 #CVPR2025

📄 Paper: arxiv.org/abs/2503.15683
🔗 Project: yb23.github.io/projects/cywd/

Today, I discovered that my first research paper just hit 100 citations. I am happy to see that this method and the provided dataset for art analysis have been reused or inspired other works.

Weakly Supervised Object Detection in Artworks : openaccess.thecvf.com/content_ECCV...