MétaCan
Menu
Back to cohort
Record W2966756268 · doi:10.11159/mvml19.103

Improving Deep Learning for Face Verification Using Color Histogram Equalization Data Augmentation

2019· article· en· W2966756268 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

VenueProceedings of the World Congress on Electrical Engineering and Computer Systems and Science · 2019
Typearticle
Languageen
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsnot available
Fundersnot available
KeywordsHistogram equalizationComputer scienceArtificial intelligenceHistogramColor normalizationFace (sociological concept)Computer visionColor histogramPattern recognition (psychology)Adaptive histogram equalizationHistogram matchingColor imageImage (mathematics)Image processing

Abstract

fetched live from OpenAlex

This paper proposes a new method of improving face verification learning using color histogram equalization by incorporating the results of deep convolutional neural networks (CNNs). The entire process of face verification using deep learning and color histogram equalization is described in detail. This research uses advanced deep learning methods for face verification tasks. Because the CNN achieves the best results for larger datasets, the main challenge is to increase the smaller dataset enhancements and validate in environments different from the training datasets. This paper presents a new training enhancement method. When the face-image datasets were small, we could use our enhanced method to expand the dataset and improve the accuracy of face verification to adopt different environments. Consequently, the accuracy reached 99.7996%, i.e., approximately 7% higher than the result trained on the original dataset.

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: Empirical · Consensus signal: none
Teacher disagreement score0.773
Threshold uncertainty score0.371

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 studies0.0000.000
Scholarly communication0.0000.001
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 head0.018
GPT teacher head0.243
Teacher spread0.226 · 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