MétaCan
Menu
Back to cohort
Record W7076252282 · doi:10.5281/zenodo.16902206

Text to image generation using BERT and GAN

2025· article· en· W7076252282 on OpenAlexaff

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2025
Typearticle
Languageen
FieldPhysics and Astronomy
TopicTheoretical and Computational Physics
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsNatural languageTask (project management)EncoderLanguage modelEncoding (memory)Generative grammarENCODEImage (mathematics)Semantics (computer science)

Abstract

fetched live from OpenAlex

Generating text to images is a difficult task that combines natural language processing and computer vision. Currently available generative adversarial network (GAN)-based models usually employ text encoders that have already been trained on image-text pairs. Nevertheless, these encoders frequently fall short in capturing the semantic complexity of unread text during pre-training, which makes it challenging to produce images that accurately correspond with the written descriptions supplied.Using BERT, a very successful pre-trained language model in natural language processing, we present a novel text-to-image generating model in order to address this problem. BERT's aptitude for picture generating tasks is improved by allowing it to encode rich textual information through fine-tuning on a large text corpus. Results from experiments on a CUB_200_2011 dataset show that our approach performs better than baseline models in both qualitative and quantitative measures.

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)0.002
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0060.003

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 head0.020
GPT teacher head0.255
Teacher spread0.235 · 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
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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicTheoretical and Computational PhysicsFrench-language works237,207