MétaCan
Menu
Back to cohort
Record W4410907310 · doi:10.21428/d82e957c.2c17961c

WSCurLe: Weakly Supervised Curriculum Learning for Foundational Vision and Language Architectures in Digital Soil Mapping

2025· article· en· W4410907310 on OpenAlexafffund
Vishvam Porwal, Stacey D. Scott, Neil D. B. Bruce, Asim Biswas

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicSemantic Web and Ontologies
Canadian institutionsUniversity of Guelph
FundersNatural Sciences and Engineering Research Council of CanadaMitacs
KeywordsCurriculumComputer scienceArtificial intelligenceNatural language processingPsychologyPedagogy

Abstract

fetched live from OpenAlex

Effective soil sampling is crucial for modern agricultural practices, requiring precise identification of viable agricultural land while excluding non-agricultural areas. While existing remote sensing approaches can distinguish broad land-use categories, they often lack the precision needed for agricultural applications. Our previous work introduced SLVVA, a satellite-based framework for land viability analysis, but its performance was limited by the representation capabilities of its vision-language encoders. In this paper, we propose WSCurLe, a novel weakly supervised curriculum learning approach that progressively fine-tunes vision-language encoders to enhance their semantic understanding while preserving fine-grained image details. Through a series of alternating training stages combining contrastive learning and reconstruction-based methods, WSCurLe significantly improves the quality of land viability segmentation. We demonstrate the effectiveness of our approach through comprehensive comparisons with state-of-the-art vision and language encoders, showing substantial improvements in both efficiency and accuracy for agricultural land analysis.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation 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: Methods · Consensus signal: Methods
Teacher disagreement score0.006
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.005
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.003
Open science0.0020.003
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0040.001

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 head0.008
GPT teacher head0.263
Teacher spread0.255 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicSemantic Web and OntologiesFrench-language works237,207