RWDS dataset is now available online. Check out the links below and let us know if you have any feedback.
14.06.2025 04:00 โ ๐ 1 ๐ 1 ๐ฌ 0 ๐ 0
๐ฃ Attending @cvprconference.bsky.social #CVPR2025?
Come see our work presented by @ferdaofli.com : Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery.
๐ Happening now!
๐ ExHall D, Poster #280
๐ Project Page | ๐ RWDS Dataset
#DomainGeneralisation #CVPR2025
13.06.2025 22:32 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 1
The #CVPR2025 main conference open access proceedings is up:
openaccess.thecvf.com/CVPR2025
Workshop papers will be posted shortly. Stay tuned...
03.06.2025 14:45 โ ๐ 32 ๐ 14 ๐ฌ 0 ๐ 1
Introducing RWDS: Real-World Distribution Shifts for Object Detection โ RWGAI
8/ Find out more about our work here:
๐ ๐ฃ๐ฟ๐ผ๐ท๐ฒ๐ฐ๐ ๐ฃ๐ฎ๐ด๐ฒ: rwgai.qcri.org/rwds/
๐ ๐๐ฉ๐ฃ๐ฅ ๐ฃ๐ฎ๐ฝ๐ฒ๐ฟ ๐ฃ๐ฎ๐ด๐ฒ: cvpr.thecvf.com/virtual/2025...
๐พ ๐๐ผ๐ฑ๐ฒ + ๐๐ฎ๐๐ฎ๐๐ฒ๐๐: github.com/RWGAI/RWDS
๐ ๐ฃ๐ฟ๐ฒ๐ฝ๐ฟ๐ถ๐ป๐: arxiv.org/abs/2503.19202
#CVPR2025
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
7/ ๐ฏ The work will also be featured in the ๐๐ผ๐บ๐ฎ๐ถ๐ป ๐๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐น๐ถ๐๐ฎ๐๐ถ๐ผ๐ป: ๐๐๐ผ๐น๐๐๐ถ๐ผ๐ป, ๐๐ฟ๐ฒ๐ฎ๐ธ๐๐ต๐ฟ๐ผ๐๐ด๐ต๐, ๐ฎ๐ป๐ฑ ๐๐๐๐๐ฟ๐ฒ ๐๐ผ๐ฟ๐ถ๐๐ผ๐ป๐ ๐ช๐ผ๐ฟ๐ธ๐๐ต๐ผ๐ฝ ๐ถ๐ป ๐๐ฉ๐ฃ๐ฅ ๐ฎ๐ฌ๐ฎ๐ฑ:
๐ ๐๐๐ป๐ฒ ๐ญ๐ฎ๐๐ต, ๐ฎ๐ฌ๐ฎ๐ฑ
๐ง ๐ญ๐ฎ:๐ฏ๐ฌ ๐ฝ๐บ โ ๐ฑ:๐ฌ๐ฌ ๐ฝ๐บ
๐ ๐ก๐ฎ๐๐ต๐๐ถ๐น๐น๐ฒ, ๐ง๐ก (๐๐ฉ๐ฃ๐ฅ ๐ฎ๐ฌ๐ฎ๐ฑ)
@cvprconference.bsky.social
#CVPR2025
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
6/๐ ๐๐ผ๐ถ๐ป ๐๐ ๐ถ๐ป ๐ก๐ฎ๐๐ต๐๐ถ๐น๐น๐ฒ!
๐ช๐ฒ'๐น๐น ๐ฏ๐ฒ ๐ฝ๐ฟ๐ฒ๐๐ฒ๐ป๐๐ถ๐ป๐ด:
๐ผ๏ธ ๐ฃ๐ผ๐๐๐ฒ๐ฟ #๐ฎ๐ด๐ฌ, ๐ฆ๐ฒ๐๐๐ถ๐ผ๐ป ๐ฎ
๐
๐๐
๐๐ฎ๐น๐น ๐ - @cvprconference.bsky.social ๐ฎ๐ฌ๐ฎ๐ฑ, ๐๐๐ป๐ฒ ๐ฎ๐ฌ๐ฎ๐ฑ
#CVPR2025
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
5/ ๐ง Researchers: RWDS offer is a rigorous new and realistic benchmark for studying domain generalisation in object detection.
๐ญ Industry: Use it to test model robustness in critical, high-stakes scenarios like climate and disaster response.
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
4/ We study SOTA object detectors under single- and multi-source domain generalisation. The results? ๐๐ป๐๐ผ๐น๐ฒ๐ฟ๐ฎ๐ฏ๐น๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ฑ๐ฟ๐ผ๐ฝ๐ ๐ถ๐ป ๐ป๐ฒ๐, ๐๐ป๐๐ฒ๐ฒ๐ป ๐ฎ๐ป๐ฑ ๐ผ๐๐ ๐ผ๐ณ ๐ฑ๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐๐ฐ๐ฒ๐ป๐ฎ๐ฟ๐ถ๐ผ๐, revealing the limitations of current AI models and the pressing need for robust, generalisable detection systems.
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
3/ ๐ก๐ฅ๐ช๐๐ฆ: ๐ฅ๐ฒ๐ฎ๐น-๐ช๐ผ๐ฟ๐น๐ฑ ๐๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐ฆ๐ต๐ถ๐ณ๐๐
We're introducing ๐ฅ๐ช๐๐ฆ, a benchmark suite designed to evaluate ๐ผ๐๐-๐ผ๐ณ-๐ฑ๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป (๐ข๐ข๐) ๐ด๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐น๐ถ๐๐ฎ๐๐ถ๐ผ๐ป and ๐ผ๐ฝ๐ฒ๐ป-๐๐ผ๐ฟ๐น๐ฑ ๐ฟ๐ผ๐ฏ๐๐๐๐ป๐ฒ๐๐ in object detection, using satellite imagery from critical domains such as:
๐ฆ๏ธ ๐๐น๐ถ๐บ๐ฎ๐๐ฒ ๐ญ๐ผ๐ป๐ฒ๐
๐ ๐๐น๐ผ๐ผ๐ฑ๐ฒ๐ฑ ๐ฅ๐ฒ๐ด๐ถ๐ผ๐ป๐
๐ ๐๐๐ฟ๐ฟ๐ถ๐ฐ๐ฎ๐ป๐ฒ ๐๐๐ฒ๐ป๐๐
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
2/ This work is part of my PhD research, and I'm incredibly grateful for the mentorship and support of my PhD advisors @ferdaofli.com and Dr. David Yang ๐
15.05.2025 16:37 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
1/ ๐ ๐ก๐ฒ๐ ๐ฃ๐๐ฏ๐น๐ถ๐ฐ๐ฎ๐๐ถ๐ผ๐ป ๐๐น๐ฒ๐ฟ๐: ๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ๐ถ๐ป๐ด ๐ข๐ฏ๐ท๐ฒ๐ฐ๐ ๐๐ฒ๐๐ฒ๐ฐ๐๐ผ๐ฟ๐ ๐๐ป๐ฑ๐ฒ๐ฟ ๐ฅ๐ฒ๐ฎ๐น-๐ช๐ผ๐ฟ๐น๐ฑ ๐๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐ฆ๐ต๐ถ๐ณ๐๐ ๐ถ๐ป ๐ฆ๐ฎ๐๐ฒ๐น๐น๐ถ๐๐ฒ ๐๐บ๐ฎ๐ด๐ฒ๐ฟ๐! ๐๐ฐ๏ธ
Weโre excited to announce that our paper "๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ๐ถ๐ป๐ด ๐ข๐ฏ๐ท๐ฒ๐ฐ๐ ๐๐ฒ๐๐ฒ๐ฐ๐๐ผ๐ฟ๐ ๐๐ป๐ฑ๐ฒ๐ฟ ๐ฅ๐ฒ๐ฎ๐น-๐ช๐ผ๐ฟ๐น๐ฑ ๐๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐ฆ๐ต๐ถ๐ณ๐๐ ๐ถ๐ป ๐ฆ๐ฎ๐๐ฒ๐น๐น๐ถ๐๐ฒ ๐๐บ๐ฎ๐ด๐ฒ๐ฟ๐" has been ๐ฎ๐ฐ๐ฐ๐ฒ๐ฝ๐๐ฒ๐ฑ ๐ฎ๐ #CVPR2025! ๐
A ๐งต
15.05.2025 16:37 โ ๐ 0 ๐ 1 ๐ฌ 1 ๐ 0
4/ We study SOTA object detectors under single- and multi-source domain generalisation. The results? ๐๐ป๐๐ผ๐น๐ฒ๐ฟ๐ฎ๐ฏ๐น๐ฒ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐ฑ๐ฟ๐ผ๐ฝ๐ ๐ถ๐ป ๐ป๐ฒ๐, ๐๐ป๐๐ฒ๐ฒ๐ป ๐ฎ๐ป๐ฑ ๐ผ๐๐ ๐ผ๐ณ ๐ฑ๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐๐ฐ๐ฒ๐ป๐ฎ๐ฟ๐ถ๐ผ๐, revealing the limitations of current AI models and the pressing need for robust, generalisable detection systems.
15.05.2025 15:57 โ ๐ 0 ๐ 0 ๐ฌ 0 ๐ 0
3/ ๐ก๐ฅ๐ช๐๐ฆ: ๐ฅ๐ฒ๐ฎ๐น-๐ช๐ผ๐ฟ๐น๐ฑ ๐๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป ๐ฆ๐ต๐ถ๐ณ๐๐
We're introducing ๐ฅ๐ช๐๐ฆ, a benchmark suite designed to evaluate ๐ผ๐๐-๐ผ๐ณ-๐ฑ๐ถ๐๐๐ฟ๐ถ๐ฏ๐๐๐ถ๐ผ๐ป (๐ข๐ข๐) ๐ด๐ฒ๐ป๐ฒ๐ฟ๐ฎ๐น๐ถ๐๐ฎ๐๐ถ๐ผ๐ป and ๐ผ๐ฝ๐ฒ๐ป-๐๐ผ๐ฟ๐น๐ฑ ๐ฟ๐ผ๐ฏ๐๐๐๐ป๐ฒ๐๐ in object detection, using satellite imagery from critical domains such as:
๐ฆ๏ธ ๐๐น๐ถ๐บ๐ฎ๐๐ฒ ๐ญ๐ผ๐ป๐ฒ๐
๐ ๐๐น๐ผ๐ผ๐ฑ๐ฒ๐ฑ ๐ฅ๐ฒ๐ด๐ถ๐ผ๐ป๐
๐ ๐๐๐ฟ๐ฟ๐ถ๐ฐ๐ฎ๐ป๐ฒ ๐๐๐ฒ๐ป๐๐
15.05.2025 15:57 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
2/ This work is part of my PhD research, and I'm incredibly grateful for the mentorship and support of my PhD advisors @ferdaofli.com and Dr. David Yang ๐ #CVPR2025
15.05.2025 15:57 โ ๐ 0 ๐ 0 ๐ฌ 1 ๐ 0
Hi @cvprconference.bsky.social, when is the deadline for uploading the poster/slides/videos to the virtual website? Thanks
08.05.2025 10:08 โ ๐ 1 ๐ 0 ๐ฌ 1 ๐ 0
Thank you for organising such an insightful #ML4RS workshop at @iclr-conf.bsky.social! Great talks and discussions throughout. Looking forward to the next one ๐
29.04.2025 03:37 โ ๐ 1 ๐ 0 ๐ฌ 0 ๐ 0
Sara Al-Emadi, Yin Yang, Ferda Ofli
Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery
https://arxiv.org/abs/2503.19202
26.03.2025 10:19 โ ๐ 1 ๐ 1 ๐ฌ 0 ๐ 0
Senior researcher at IMAGINE (ENPC, LIGM).
Machine learning & computer vision for 3D + geospatial + historical data.
loiclandrieu.com
Embed2Scale (E2S) pioneers AI-based data compression in the Copernicus Programme, aiming to overcome the challenge of handling vast geospatial information.
Through advanced AI-driven compression techniques, the project aims to streamline data transfer and
LโInstitut national de l'information gรฉographique et forestiรจre produit des donnรฉes et reprรฉsentations du territoire national pour observer, comprendre et anticiper ses รฉvolutions. ๐บ๏ธ๐ณ
๐ https://kytelink.com/ign
#Opendata #Carte #Gรฉographie #Forรชt
PhD - R&D Engineer at French Mapping Agency @ignfrance.bsky.social working on Deep Learning and computer Vision for Earth observation
Research faculty @ImagineENPC. https://gulvarol.github.io/
PhD student @ TUM with Daniel Cremers
Computer Vision & Machine Learning researcher at NAVER LABS europe
she/her - https://dlarlus.github.io/
Assistant Professor at Ecole Polytechnique, IP_Paris// Before: Oxford_VGG, Inria Grenoble // multimodality, genAI enthusiast // happy mum+dog_mum // opinions: mine
Professor of Computer Vision and AI at TU Munich, Director of the Munich Center for Machine Learning mcml.ai and of ELLIS Munich ellismunich.ai
cvg.cit.tum.de
๐ PhD Student in Robotics at ETH Zรผrich
๐ Computer Vision, 3D Reconstruction, Structure-from-Motion, SLAM, Geometry
๐Postdoc in Politecnico di Milano and EIEE/CMCC
๐ I do research on AI for Vision, Graphics, Economics & Climate Change.
๐ป https://carlosrodriguezpardo.es
Madrid โ๏ธ Milano
Teaching blind robots to see... I am a scientist and Reader at the University of Glasgow, interested in AI, Computer Vision & Robotics.
Student Researcher @ RAI Institute, MSc CS Student @ ETH Zurich
visual computing, 3D vision, spatial AI, machine learning, robot perception.
๐Zurich, Switzerland
IJCAI is the longest-running premier international AI research conference since 1969. ๐ Connect across domains and feel the pulse of AI. ๐๏ธ #IJCAI2025 โ16-22 August 2025โMontreal ๐จ๐ฆ
AI Pioneer, AI+Science, Professor at Caltech, Former Senior Director of AI at NVIDIA, Former Principal Scientist at AWS AI.
Ask me about Reinforcement Learning
Research @ Sony AI
AI should learn from its experiences, not copy your data.
My website for answering RL questions: https://www.decisionsanddragons.com/
Views and posts are my own.
MIT's Computer Science & Artificial Intelligence Laboratory (CSAIL). Media Inquiries: rachelg@csail.mit.edu
The official account of the Stanford Institute for Human-Centered AI, advancing AI research, education, policy, and practice to improve the human condition.
Stanford University Press has been publishing books across the humanities, social sciences, law, business, and other areas since 1892.
