TESSERA v2: Scaling Pixel-wise Earth Foundation Models
Large-scale controlled experiments reveal optimal scaling strategies for Earth-observation foundation models, enabling efficient training and deployment through encoder growth, dow…
Hugging Face · Daily Papers
·Zhengpeng Feng, Sadiq Jaffer
·
·▲ 2 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Zhengpeng Feng, Sadiq Jaffer, Ira Shokar, Jovana Knezevic, Mark Elvers, Clement Atzberger
- 2 upvotes da comunidade
- Temas: pixel-wise Earth-observation, foundation models, spatial embeddings, Barlow Twins, downstream tasks, encoder
Resumo
Resumo original (em inglês), extraído do paper:
Large-scale controlled experiments reveal optimal scaling strategies for Earth-observation foundation models, enabling efficient training and deployment through encoder growth, downstream performance selection, and model distillation.Onde ler
// relacionados
Leia também
Blog
Flight attendants freaked out that Google is buying tons of Spirit employee data
Blog
Attackers are using AI to build exploits for industrial control systems, U.S. agencies warn
Blog
AI labs are failing to keep their own systems in check
Editorial