Had a blast talking about masked autoencoders for satellite data yesterday at EGU. I am here until tomorrow still. Feel free to reach out :)
I'll be at EGU in Vienna! Reach out or swing by ESSI1.1 - Strategies and Applications of AI and ML in a Spatiotemporal Context. My PICO spot is on Wednesday, 26 April 2023, 14:19. My "screen poster" will be Wednesday, 26 April 2023, 14:33-15:45 at PICO screen PICO2.8.
Lukas Kondmann retweeted
🚨1 WEEK LEFT🚨 In-person applications for @ClimateChangeAI’s second summer school are closing on Jan 31. Don’t miss this opportunity! (Applications for the virtual program will remain open)
More details here: climatechange.ai/events/summ…
Excited to announce the second @ClimateChangeAI Summer School (Jun-Aug 2023)!👩🎓☀️
Are you an #AI or #DataScience expert who wants to tackle #ClimateChange? Are you a #climate expert trying to use #ML in your work?
Apply to our virtual & in-person programs: climatechange.ai/events/summ…
New ChatGPT impressions (chat.openai.com/chat)
Chat Skills 10/10.
Lord of the Rings Knowledge 6/10
Lukas Kondmann retweeted
You can hire me! 👇
IIES Job Market Candidate Tillmann von Carnap’s @TCarnap job market paper asks how rural marketplaces shape their surroundings and how this age-old way of trading can be leveraged for development. 1/5 bit.ly/3X3XiLx
after the great success last year, we have a new edition of the grants program at @ClimateChangeAI :) check it out!
We're excited to announce the 2023 @ClimateChangeAI Innovation Grants, supported by the Quadrature Climate Foundation & @DeepMind.👩🔬💵
We’ll fund projects at the intersection of #ClimateChange & #ML w/ up to $150k each, for a total of $1.2M.
Learn more: climatechange.ai/calls/innov…
I'm turning my hobby of talking people into climate-related careers into something official ;) So excited to join @ClimateChangeAI!
Our Programs Committee is growing by 9 new members! First off, a big welcome to @fib_11235, Ashesh Chattopadhyay, @daniel_spokoyny, @_jorgemontalvo_ and @kondmann.👋🎉
Lukas Kondmann retweeted
JMLR has recently launched a Special Issue on ML for addressing problems of climate change! We welcome all submissions which use machine learning to address problems of climate change, including mitigation, adaptation, and climate science. [1/4]
Lukas Kondmann retweeted
I'm moving to Boston! 🎉🚀
I am incredibly excited to start as a postdoctoral researcher at @MSFTResearch in the New England (@MSRNE) lab in fall. I'll continue to work on geospatial problems, improving our cities & tackling climate change with machine learning.🤖🛰️🌏
Excited to share that today is my first day as a PhD summer intern at @Planet. I'll be working with their analytics team on detecting changes in time-series of satellite imagery. It's mostly remote but will be in their Berlin office occasionally :)
Did not get enough of CVPR last week or you could not make it in person? Swing by today at the virtual poster session 10-12 am CDT/5-7pm CET Floor 22 Poster 4 to talk about our DynamicEarthNet paper!
Our work DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation will be presented at #CVPR2022!
➡️ arxiv.org/abs/2203.12560
Tackling climate change is the defining task of our generation, so what part can the vision community play in that? 🧵⬇️
Lukas Kondmann retweeted
Super excited to present our work @CVPR today afternoon! Join us at the poster 237 from 14.30-17.00 🛰🗺🌏
Our work DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation will be presented at #CVPR2022!
➡️ arxiv.org/abs/2203.12560
Tackling climate change is the defining task of our generation, so what part can the vision community play in that? 🧵⬇️
Lukas Kondmann retweeted
What happens if you train a Vision Transformer with a self-supervised dense clustering task?
In our #CVPR2022 paper we find that our method, Leopart 🐆, learns expressive object part embeddings.
Paper: arxiv.org/abs/2204.13101
Code: github.com/MkuuWaUjinga/leop…
🧵1/n
Lukas Kondmann retweeted
Interested in land use dynamics on the Earth's surface? Check our #DynamicEarthNet dataset -- daily, multi-spectral satellite observations of 75 AOIs across the globe with imagery from #Planetscope and #Sentinels, paired with high quality #LULC labels #AI4EO #CVPR
Swing by the ICLR PML4DC poster session to talk about our work on crop type classification early in the season. This was part of my research fellowship with @WFP. The poster session starts in an hour. The paper is here: pml4dc.github.io/iclr2022/pd…
Is it Christmas already? Amazing stuff @Maja4EO
HAPPY RELEASE DAY!!! 🥳🌾🌍
A year of data collection, an unheard number of e-mails and an entire new crop and agriculture taxonomy later, we've made it! 😁
From today on, the #EuroCrops vector data is available via our GitHub repo: github.com/maja601/EuroCrops
Our DynamicEarthNet benchmark was accepted as a #CVPR2022 paper! We hope to give change detection from space its ImageNet moment. This took more than 2 years to build so I'm gonna be offended if you don't use it ;) see you in New Orleans!
Our work DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation will be presented at #CVPR2022!
➡️ arxiv.org/abs/2203.12560
Tackling climate change is the defining task of our generation, so what part can the vision community play in that? 🧵⬇️
Update: Our paper on SiROC, an unsupervised change detection method for optical images is now finally out in IEEE TGRS ieeexplore.ieee.org/document… It's open access and you can find the code here: github.com/lukaskondmann/SiR… This was fun! @xiaoxiang_zhu @Zhu_XLab @bschoelkopf @lealtaixe
Interested in #ChangeDetection in satellite time series data, but has no label? Check our recent work @Zhu_XLab @ai4eo_de
Spatial Context Awareness for #Unsupervised
Change Detection in Optical Satellite Images by @kondmann @TokerAysim @sudipansaha @bschoelkopf @lealtaixe


























