MétaCan
Menu
Back to cohort
Record W7110688175

Uzun kuyruklu görsel tanımada sınıf dengesizliğinin öz boyut kullanımı ile azaltılması

2024· dissertation· W7110688175 on OpenAlexfundno aff

Bibliographic record

VenueOpenMETU (Middle East Technical University) · 2024
Typedissertation
Language
FieldComputer Science
TopicImbalanced Data Classification Techniques
Canadian institutionsnot available
FundersCanadian Institute for Advanced Research
KeywordsClass (philosophy)Field (mathematics)EstimationCalibrationCurse of dimensionalityImage (mathematics)
DOInot available

Abstract

fetched live from OpenAlex

Natural image datasets used in the field of visual recognition are often imbalanced in terms of the number of samples between class categories in the dataset. This problem, defined commonly as class imbalance, results in sub-optimal performance on these under-represented classes for deep learning models which are trained with such datasets. Attempts to remedy this problem include re-sampling, loss re-weighting and other calibration methods which generally use the number of samples as the primary factor in their mitigation strategy, ignoring other factors. In this thesis, we argue that model performance in a dataset depends on the difficulty of individual class categories as well as the number of samples present in the dataset. We use the concept of intrinsic dimensionality to express this idea of difficulty and explore the different definitions and estimation strategies for calculating ID inside a dataset. We further investigate the relationship between ID and class imbalance. Lastly, we report our results on using class ID estimation for class imbalance mitigation on long-tailed variations of natural image datasets -- MNIST-LT, CIFAR-10-LT and CIFAR-100-LT.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Open science, Research integrity, Insufficient payload (model declined to judge)
Consensus categoriesMeta-epidemiology (narrow), Research integrity, Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.899
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0020.003
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.008
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0140.005
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0010.005

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 head0.043
GPT teacher head0.242
Teacher spread0.199 · 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; both teacher heads agree on what is shown here.

Study designNot applicable
Domainnot available
GenreMethods

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueOpenMETU (Middle East Technical University)Same topicImbalanced Data Classification TechniquesFrench-language works237,207