MétaCan
Menu
Back to cohort
Record W4281381440 · doi:10.1061/9780784483893.028

Training a Visual Scene Understanding Model Only with Synthetic Construction Images

2022· article· en· W4281381440 on OpenAlexaff
Jinwoo Kim, Daeho Kim, Julianne Shah, Sang Hyun Lee

Bibliographic record

VenueComputing in Civil Engineering 2021 · 2022
Typearticle
Languageen
FieldEngineering
TopicInfrastructure Maintenance and Monitoring
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceSynthetic dataArtificial intelligenceEconomic shortageScalabilityTask (project management)Deep learningTraining setMachine learningDomain (mathematical analysis)Artificial neural networkDeep neural networksComputer visionPattern recognition (psychology)DatabaseEngineering

Abstract

fetched live from OpenAlex

While the use of deep neural networks (DNN) for computer vision is increasing in the construction domain, the shortage of training data sets prevents such models from achieving their maximum potential. To address this issue, we investigate the potential of using synthetic data for vision model development. Specifically, we synthesize construction images and train a DNN model only with the synthetic data. We then evaluate the performance of the synthetic data-trained model on a worker detection task, and the results demonstrate the great potential of synthetic images: 97.3% of mean average precision. Given the benefits of synthetic data—it is possible to automatically create an unlimited number of images without manual labeling—this finding is promising. Moreover, this approach can be readily applied to other computer vision tasks, without requiring the manual labeling. This finding will enable the creation of more accurate and scalable DNN models for construction applications.

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 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 categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.701
Threshold uncertainty score1.000

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 studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
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 head0.015
GPT teacher head0.211
Teacher spread0.196 · 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 teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations6
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueComputing in Civil Engineering 2021Same topicInfrastructure Maintenance and MonitoringFrench-language works237,207