MétaCan
Menu
Back to cohort
Record W3209365819 · doi:10.1145/3459637.3482458

Norma

2021· article· en· W3209365819 on OpenAlexaff
Mahsa Keramati, Zahra Zohrevand, Uwe Glässer

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsSimon Fraser University
Fundersnot available
KeywordsDiscriminative modelComputer scienceArtificial intelligenceCentroidDomain (mathematical analysis)Cluster analysisPattern recognition (psychology)Class (philosophy)Feature (linguistics)Process (computing)Machine learningAdaptation (eye)Image (mathematics)Feature extractionDomain adaptationFeature learningMathematics

Abstract

fetched live from OpenAlex

Unsupervised domain adaptation is the problem of transferring extracted knowledge from a labeled source domain to an unlabeled target domain. To achieve discriminative domain adaptation recent studies take advantage of target sample pseudo-labels to impose class-aware distribution alignment across the source and target domains. Still, they have some shortcomings such as making decisions based on inaccurate pseudo-labeled samples that mislead the adaptation process. In this paper, we propose a progressive deep feature alignment, called Norma, to tackle class-aware unsupervised domain adaptation for image classification by enforcing inter-class compactness and intra-class discrepancy through a hybrid learning process. To this end, Norma's optimization process is defined based on a novel triplet loss which not only addresses soft prototype alignment but also pushes away multiple negative centroids. Also, to extract maximum discriminative domain knowledge per iteration, we propose a joint positive and negative learning procedure along with an uncertainty-guided progressive pseudo-labeling on the basis of prototype-based clustering and conditional probability. Our experimental results on several benchmarks demonstrate that Norma outperforms the state-of-the-art methods.

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)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.983
Threshold uncertainty score0.000

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0020.003
Open science0.0030.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0170.015

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 head0.013
GPT teacher head0.225
Teacher spread0.212 · 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.

Study designNot applicable
Domainnot available
GenreOther

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

Citations1
Published2021
Admission routes1
Has abstractyes

Explore more

Same topicDomain Adaptation and Few-Shot LearningFrench-language works237,207