MétaCan
Menu
Back to cohort
Record W4288075349 · doi:10.18280/ts.390319

A Deep Learning-Based Cluster Analysis Method for Large-Scale Multi-Label Images

2022· article· en· W4288075349 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.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueTraitement du signal · 2022
Typearticle
Languageen
FieldComputer Science
TopicText and Document Classification Technologies
Canadian institutionsnot available
Fundersnot available
KeywordsArtificial intelligencePattern recognition (psychology)Computer scienceImage (mathematics)GraphFeature extractionScale (ratio)Feature (linguistics)Theoretical computer science

Abstract

fetched live from OpenAlex

Large-scale multi-label image classification requires determining the presence or absence of a target object in a large number of sample images. For highly specialized and complex multi-label image sets, it is especially important to ensure the accuracy of image classification. Traditional deep learning models usually don’t take into account image-label correlation constraints when classifying multi-label images, and the strategy of classifying images based only on their own features greatly limits the model performance. In this context, this paper focuses a deep learning-based cluster analysis method for large-scale multi-label images. We constructed a model for large-scale multi-label image category recognition, which consists of a global image feature extraction module, a feature activation vector generation module and an image category inter-label connection module. Using a graph convolutional network (GCN), we aggregated the information of image category label nodes in the constructed multi-label graph structure, while exploring the correlation between image category labels. A detailed description is presented on how to introduce the attention mechanism into the constructed model mentioned above for image category recognition. Experimental results have validated the effectiveness of the constructed model.

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)0.001
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: Methods · Consensus signal: Methods
Teacher disagreement score0.559
Threshold uncertainty score0.660

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.000
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 head0.026
GPT teacher head0.300
Teacher spread0.275 · 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