MétaCan
Menu
Back to cohort
Record W4292970091 · doi:10.1109/lgrs.2022.3201489

SatViT: Pretraining Transformers for Earth Observation

2022· article· en· W4292970091 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueIEEE Geoscience and Remote Sensing Letters · 2022
Typearticle
Languageen
FieldEngineering
TopicRemote-Sensing Image Classification
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceTransformerArtificial intelligenceTraining setMachine learningPattern recognition (psychology)VoltageEngineering

Abstract

fetched live from OpenAlex

Despite the enormous success of the ’pre-training and fine-tuning’ paradigm, widespread across machine learning, it has yet to pervade remote sensing (RS). To help rectify this, we pre-train a vision transformer (ViT) on 1.3 million satellite-derived RS images. We pre-train SatViT using a state-of-the-art self-supervised learning algorithm called masked autoencoding (MAE), which learns general representations by reconstructing held-out image patches. Crucially, this approach does not require annotated data, allowing us to pre-train on unlabeled images acquired from Sentinel-1 & 2. After fine-tuning, SatViT outperforms state-of-the-art ImageNet and RS-specific pre-trained models on both of our downstream tasks. We further improve overall accuracy (by 3.2% and 0.21%) by continuing to pre-train SatViT—still using MAE—on the unlabelled target datasets. Most importantly, we release our code, pre-trained model weights, and tutorials aimed at helping researchers fine-tune our models. (https://github.com/antofuller/SatViT).

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.972
Threshold uncertainty score0.619

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.025
GPT teacher head0.222
Teacher spread0.197 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it