MétaCan
Menu
Back to cohort

Quantitative Analysis of Transfer Learning for Image Classification

2022· article· en· W4285816564 on OpenAlexaff
Imran Shafiq Ahmad, Aishwarya Yelishetty

Bibliographic record

Venue2022 IEEE 7th International conference for Convergence in Technology (I2CT) · 2022
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsUniversity of Windsor
Fundersnot available
KeywordsTransfer of learningComputer scienceArtificial intelligenceMachine learningTask (project management)Inductive transferImage (mathematics)Contextual image classificationRobot learningEngineering

Abstract

fetched live from OpenAlex

This work is a quantitative analysis of various transfer learning methods and some incremental learning techniques using the task of image classification. We also analyze the assumptions under which transfer learning should be applied and how true these assumptions are in most of the real-world scenarios along with a brief description of the disadvantages such as decreased accuracy, biased models, etc. of using transfer learning in general and when applied at the wrong problem. An extensive study is carried out to explore thoroughly the relevant literature and the results obtained after the analysis are also presented in the tabulated form at the end of the paper. Last but not least we have explored the problems with transfer learning frameworks and ways in which we can overcome some of them.

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)0.001
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 score0.959
Threshold uncertainty score0.760

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.002
Science and technology studies0.0000.000
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 head0.063
GPT teacher head0.336
Teacher spread0.273 · 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.

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
Published2022
Admission routes1
Has abstractyes

Explore more

Same venue2022 IEEE 7th International conference for Convergence in Technology (I2CT)Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207