Caleb Robinson
@calebrob6
Followers
683
Following
797
Media
8
Statuses
179
Research scientist on Microsoft's AI for Good team.
Joined January 2016
Working on transfer learning and foundation models in remote sensing? We invite you to submit abstracts to our session IN005 at #AGU25 ( https://t.co/IeKBxVEJdB…) organized by @sherwang (MIT),@hannah_kerner (Arizona State), Siddharth Sachdeva, and me (Stanford).
0
8
25
Researchers at @Microsoft’s AI for Good Lab, in collaboration with @WildNatureInst, have developed GIRAFFE, an open-source AI-driven system to automate the identification of individual giraffes. Learn more about our new AI-powered tool. https://t.co/A8h9qSSrwH
0
3
15
I'm hiring for a machine learning data scientist & research assistant for summer 2025! Join me on a project on invasive species management with an innovative startup doing on-the-ground removal of environmentally destructive invasives. Paid, full-time w/ possibility to extend.
28
64
627
An expanded version of our TorchGeo paper has been accepted to ACM TSAS @TheOfficialACM In addition to even more benchmarks on remote sensing datasets, we provide a thorough survey of open-source libraries for deep learning for geospatial data @calebrob6 @BDataScientist
2
15
67
NOAA has posted satellite imagery from the areas affected by the Eaton, Hurst, and Palisades wildfires. The imagery is available through Maxar's Open Data program to support the emergency response community and the public: https://t.co/EEETAGRURB Disaster-specific @FEMA resources
6
105
218
The Climate Change AI workshop at NeurIPS tomorrow will be livestreamed for free, even if you weren't able to register for NeurIPS (which was oversubscribed this year)!
Another highlight of our #NeurIPS2024 workshop on Sunday will be a panel discussion on small vs big models in ML for climate impact, featuring Chris Bretherton, Anamika Dubey & @BDilkina. Stream the whole workshop live & for free via our website: https://t.co/6cDIBuE7p6
0
13
44
🚨Our new review paper "Better, not just more: Data-centric ML for Earth Observation" 🌐🤖🛰️🔍 has finally been published in GRSM. Shifting the focus from models to data offers new possibilities to improve accuracy, generalization, and real-world impact: https://t.co/iypdTVnZ1t
0
16
59
'How geospatial AI can help us understand global scale challenges such as climate change or food insecurity. '- @tammyglazer
#Geospatial #GeospatialAI
1
2
3
It was so fun working on this with @hannah_kerner, @jacobsn, @opencholmes, @GhoshPrivate, @Adeal_GIS, @matthmohr, @rdodhia, @BDataScientist, Snehal Chaudhari, Eddie Choi, and Jennifer Marcus!
1
0
6
a baseline for training and testing global models. Paper: https://t.co/qQcrOkPubD Code: https://t.co/0VHzZA7w2D Website:
1
0
8
Here's output from running a model on two Sentinel-2 scenes (straight off the Planetary Computer) from part of Sudan. You can do this too! -- see code for inference at our repo https://t.co/0VHzZA7w2D. This doesn't solve field boundary delineation by any stretch, but serves as
1
0
5
1/ We released Fields of the World (FTW)-- a new satellite imagery + field boundary dataset with samples from 24 countries (now downloadable via torchgeo)! One cool part of this work is that we find that models trained on FTW have decent zero-shot performance in new locations:
I'm so excited to finally introduce Fields of The World (FTW!) - the largest & most diverse ML dataset for field instance segmentation in satellite images. FTW has >70k samples from 24 countries (4 continents), with semantic & instance labels + Sentinel-2 RGB-NIR from 2 dates. 🧵
1
21
72
5/ A massive thank you, as always, to all our contributors! The PRs, bug reports, discussions, and new research contributions you add make TorchGeo possible. Let's continue to make it easy to combine deep learning with geospatial data!! See you again for 0.7.0 😀
0
0
2
4/ We've also done a lot of work on reproducibility. E.g. with Radiant MLHub shutting down, we've successfully migrated key datasets to Source Cooperative and AWS. This migration not only ensures continuity but also allowed us to simplify code!
1
0
1
3/ One of the new models, DOFA ( https://t.co/lMhtJ730U5), supports RGB, SAR, MSI, and HSI with any number of spectral bands. This, along with the flexibility of TorchGeo's RasterDatasets, allows users to test pre-trained models on their downstream use case nearly out-of-the-box.
1
0
2
2/ Specifically, this release contains 18 new datasets, 15 new Lightning Datamodules (making it easy to train/validate/and test models on a given dataset) and 27 new pre-trained models (specialized for different types of EO data).
1
0
2
1/🚀TorchGeo 0.6.0 is here! TorchGeo is a python library for deep learning with geospatial datasets. This large update contains new datasets, foundation models, and more -- over 11 months of hard work from many contributors! See more details:
github.com
TorchGeo 0.6.0 Release Notes TorchGeo 0.6 adds 18 new datasets, 15 new datamodules, and 27 new pre-trained models, encompassing 11 months of hard work by 23 contributors from around the world. High...
1
41
216
Attention maps of @Meta & @WorldResources DINO model compared to ImageNet pretrained DINO on some UCMerced dataset samples. left-to-right: (image, meta/wri, imagenet).
4
8
54
Our new paper, "Satellite Data Shows Resilience of Tigrayan Farmers in Crop Cultivation During Civil War," shows that despite widespread disruptions to ag & other sectors during the Tigray War, Tigrayan farmers were largely able to sustain cultivation. https://t.co/WvLyThW2vg
2
5
39
🎉Tomorrow is the first #NeurIPS2023 workshop on Computational Sustainability! 🎙️✨We can't wait to host an amazing panel during the workshop including @Grant_Van_Horn, @calebrob6, Emily Aiken, Carla Gomes, and Eric Ornstein! 🗓️Check out our schedule on https://t.co/YStuoUmbWM
0
7
16