Lightnews — Scholar-powered news

Guillaume Astruc @gastruc.bsky.social · Aug 18

Super interesting to see pure SSL outperforms text alignement on a super competitive but text-aligned suited task 🤯

Nicolas Dufour @nicolasdufour.bsky.social · Aug 18

🚀 DinoV3 just became the new go-to backbone for geoloc!
It outperforms CLIP-like models (SigLip2, finetuned StreetCLIP)… and that’s shocking 🤯
Why? CLIP models have an innate advantage — they literally learn place names + images. DinoV3 doesn’t.

2

Guillaume Astruc @gastruc.bsky.social · Jun 11

🛰️ At #CVPR2025 presenting "AnySat: An Earth Observation Model for Any Resolutions, Scales, and Modalities" - Saturday afternoon, Poster 355!
If you're here and want to discuss geolocation or geospatial foundation models, let's connect!

3 13

Reposted by Guillaume Astruc

Nicolas Gonthier @nicaogr.bsky.social · Jun 11

📢 FLAIR-HUB dataset
A new large-scale, multimodal dataset for land cover and crop type mapping
🤗 Dataset: huggingface.co/datasets/IGN...
📄 Preprint: arxiv.org/abs/2506.07080
🤗 Pretrained models: huggingface.co/collections/...
💻 Code: github.com/IGNF/FLAIR-HUB
🌐 Project : arxiv.org/abs/2506.07080

FLAIR-HUB: Large-scale Multimodal Dataset for Land Cover and Crop Mapping

The growing availability of high-quality Earth Observation (EO) data enables accurate global land cover and crop type monitoring. However, the volume and heterogeneity of these datasets pose major pro...

arxiv.org

1 8 18

Reposted by Guillaume Astruc

Elliot Vincent @elliotvincent.bsky.social · Jun 11

I will be presenting our work on the detection of archaeological looting with satellite image time series at CVPR 2025 EarthVision workshop tomorrow!

Honored and grateful that this paper received the best student paper award!

1 6 15

Reposted by Guillaume Astruc

Ryan @ryanboustany.bsky.social · May 23

📢 New preprint!
“When majority rules, minority loses: bias amplification of gradient descent”

We often blame biased data but training also amplifies biases. Our paper explores how ML algorithms favor stereotypes at the expense of minority groups.

➡️ arxiv.org/abs/2505.13122

(1/3)

When majority rules, minority loses: bias amplification of gradient descent

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 tasks, ...

arxiv.org

1 2 3

Guillaume Astruc @gastruc.bsky.social · Apr 30

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: arxiv.org/abs/2412.14123
🌐 Project: gastruc.github.io/anysat

3 9

Reposted by Guillaume Astruc

Imagine-ENPC @imagineenpc.bsky.social · Apr 30

Looking forward to #CVPR2025! We will present the following papers:

1 7 28

Reposted by Guillaume Astruc

Nicolas Gonthier @nicaogr.bsky.social · Apr 28

Introducing HySCDG #CVPR2025, a generative pipeline for creating a large hybrid semantic change detection for Earth Observation using Stable Diffusion and ControlNet ! 🗺️🛩️

📄 Paper: arxiv.org/abs/2503.15683

The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generation

Bi-temporal change detection at scale based on Very High Resolution (VHR) images is crucial for Earth monitoring. This remains poorly addressed so far: methods either require large volumes of annotate...

arxiv.org

1 5 15

Reposted by Guillaume Astruc

Antoine Guédon @antoine-guedon.bsky.social · Apr 3

💻We've released the code for our #CVPR2025 paper MAtCha!

🍵MAtCha reconstructs sharp, accurate and scalable meshes of both foreground AND background from just a few unposed images (eg 3 to 10 images)...

...While also working with dense-view datasets (hundreds of images)!

4 16 40

Reposted by Guillaume Astruc

David Picard @davidpicard.bsky.social · Mar 21

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷

Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...

Big 🧵👇 with details!

8 51 140

Reposted by Guillaume Astruc

Imagine-ENPC @imagineenpc.bsky.social · Mar 14

Starter pack including some of the lab members: go.bsky.app/QK8j87w

11 24

Reposted by Guillaume Astruc

Thibaut Loiseau @thibautloiseau.bsky.social · Feb 28

🧩 Excited to share our paper "RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges" (arxiv.org/abs/2502.19955) accepted to #CVPR2025! We created a benchmark that systematically evaluates image matching methods across well-defined geometric difficulty levels. 🔍

2 7 19

Reposted by Guillaume Astruc

Nicolas Dufour @nicolasdufour.bsky.social · Feb 20

Weights for CAD are finally available. It's one of the smallest diffusion models on the market, achieving performance close to SD and Pixart, featuring a Perceiver-like architecture.
We leverage our coherence aware training to improve the textual understanding

David Picard @davidpicard.bsky.social · Feb 20

🚨 Just a quick note that following requests, we trained a 512px version of our Coherence-Aware Diffusion model (CVPR'24) and updated the paper on arxiv: arxiv.org/abs/2405.20324

It has a package and pretrained models!

🖥️ nicolas-dufour.github.io/cad.html
🤖 github.com/nicolas-dufo...