Paper
SatMAE: pre-training transformers for temporal and multi-spectral satellite imagery
External resource. Not made or verified by Public Protocol.
A NeurIPS 2022 paper adapting masked autoencoders to satellite time series and spectral band groups, reporting gains of up to 7 per cent on supervised benchmarks and up to 14 per cent in transfer learning for land cover classification.
https://arxiv.org/abs/2207.08051
- Maintainer
- Yezhen Cong, Samar Khanna and others; arXiv
- Licence, as stated at its source
- CC BY 4.0
- Open or commercial
- Open
- Maturity
- PrototypeOur reading, 16 November 2026
- Safety
- S0
- Review
- Listed 16 November 2026by Public Protocol editors
- Checked
- 16 November 2026
- Next check due
- 16 May 2027
- Steward
- Public Protocol editors
Where it sits in the blueprint
- Stages
Learn
- Elements it supports
- Context
Climate, setting, scale, cost and skill: not stated in this entry. Check the source against your own place and numbers.
Verification
No verification is recorded on Public Platform for this entry. Records are added when someone reads it for accuracy, reviews it with a stated qualification, builds it or measures it.
Record
- How it came in
Seed catalogue, 16 November 2026. Listed from the seed research of 2026-11-16. The source was opened and described on the date shown.
- Licence
CC BY 4.0. Read at https://arxiv.org/abs/2207.08051. How licences are recorded
- Something wrong?