MétaCan
Menu
Back to cohort
Record W4312917662 · doi:10.21512/commit.v16i2.8144

Observing Pre-Trained Convolutional Neural Network (CNN) Layers as Feature Extractor for Detecting Bias in Image Classification Data

2022· article· en· W4312917662 on OpenAlexaboutno aff
Amadea Claire Isabel Ardison, Mikhaya Josheba Rumondang Hutagalung, Reynaldi Chernando, Tjeng Wawan Cenggoro

Bibliographic record

VenueCommIT (Communication and Information Technology) Journal · 2022
Typearticle
Languageen
FieldComputer Science
TopicData Mining and Machine Learning Applications
Canadian institutionsnot available
Fundersnot available
KeywordsConvolutional neural networkMNIST databaseComputer scienceFeature (linguistics)Artificial intelligenceExtractorKernel (algebra)Pattern recognition (psychology)Feature extractionWorkflowLayer (electronics)Image (mathematics)Convolution (computer science)Deep learningArtificial neural networkDatabaseMathematicsEngineering

Abstract

fetched live from OpenAlex

Detecting bias in data is crucial since it can pose serious problems when developing an AI algorithm. The research aims to propose a novel study design to detect bias in image classification data by using pretrained Convolutional Neural Network (CNN) layers as a feature extractor. There are three datasets used in the research with varying degrees of complexity, those are low, medium, and high complexity. There are Modified National Institute of Standards and Technology (MNIST) Digits, batik collections (Parang, Megamendung, and Kawung), and Canadian Institute for Advanced Research (CIFAR-10) datasets. Then, the researchers make a baseline workflow and substitute a step-in feature extraction with a convolution using the first pre-trained CNN layer and each of its kernels. Then, the researchers evaluate the effect of the experiments using accuracy. By observing the effect of the individual kernel, the research can better make sense of what happens inside a CNN layer. The research finds that color in the image is an essential factor when working with CNN. Furthermore, the proposed study design can detect bias in image classification data where it is related to the color of the image. Detecting this bias early is important in helping developers to improve AI algorithms.

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)0.005
metaresearch head score (Gemma)0.020
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: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.020
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.001
Scholarly communication0.0010.003
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

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 head0.060
GPT teacher head0.314
Teacher spread0.254 · 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

Citations2
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueCommIT (Communication and Information Technology) JournalSame topicData Mining and Machine Learning ApplicationsFrench-language works237,207