Robin Cole
@robmarkcole
Followers
10K
Following
57K
Statuses
8K
Tackling the worlds toughest challenges with AI & ML applied to satellite & aerial imagery https://t.co/QmbOWgdfAZ
London, England
Joined April 2009
🏠 the Open Buildings 2.5D Temporal Dataset is freely available to support the work of policymakers, humanitarian organizations and others working in the Global South
From electricity access to disaster response, knowing the location of buildings is crucial. The Open Buildings project now includes temporal data, unlocking understanding of how regions & their needs change over time. Check out the data & learn more →
0
2
10
Inference on Computer Vision for Earth Observation: a panel discussion on the MLM STAC Extension
NEXT WEEK: Don't forget to join our panel discussion alongside Radiant Earth, @CRIM_ca and @Terradue. We'll discuss the MLM STAC Extension, the challenge it solves, its use cases, and why model developers should adopt it, along with Raster Inference—a serverless computer vision solution that extracts valuable insights from aerial imagery. Register here:
0
0
11
🧊Globally scalable glacier mapping by deep learning matches expert delineation accuracy
#3 GlaViTU This paper presents a novel world-wide dataset and a convolutional-transformer, Glacier-VisionTransformer-U-Net (GlaViTU), for multitemporal and global glacier mapping. ⬆️ relevant task and nice results ⬇️ weak zero-shot transferability?
0
0
7
🌲 A Sentinel-2 machine learning dataset for tree species classification in 🇩🇪
New data description paper: A Sentinel-2 machine learning dataset for tree species classification in Germany
0
11
67
It now has a name - “vibe coding”
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.
0
0
1
0
0
12
Can Location Embeddings Enhance Super-Resolution of Satellite Imagery?
#2 Can Location Embeddings Enhance Super-Resolution of Satellite Imagery? It looks like they can :) ⬆️: validating it on a real-world task ⬇️: is it super-resolution or mapping S2 to NAIP?
0
5
24