MétaCan
Menu
Back to cohort

Encoding High-Level Features: An Approach To Robust Transfer Learning

2022· article· en· W4292387707 on OpenAlexafffund
Laurent Yves Emile Ramos Cheret, Thiago Eustaquio Alves de Oliveira

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicDomain Adaptation and Few-Shot Learning
Canadian institutionsLakehead University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceAutoencoderArtificial intelligenceTransfer of learningPattern recognition (psychology)Convolutional neural networkENCODERobustness (evolution)Encoding (memory)Contextual image classificationFeature (linguistics)Feature learningDeep learningMachine learningImage (mathematics)

Abstract

fetched live from OpenAlex

Transfer Learning (TL) plays a vital role in image classification systems based on Deep Convolutional Neural Networks (DCNNs). Systems employing such technique may be susceptible to distortions on images, motivating the development of robust DCNNs capable of facing these problems. Unfortunately, changes in the architecture of DCNNs are sometimes specific to a kind of distortion and result in models that need to be retrained from scratch. This work proposes the use of autoencoders as intermediaries between pre-trained DCNNs and classifiers, delegating the denoising task to this architecture trained to encode feature maps. The classifiers are then trained to map the inputs from the autoencoder latent spaces to their respective classes. Models employing this approach achieved 3% to 4% increase in accuracy and 50% to 70% reduction in loss on the CIFAR10 and CIFAR100 datasets. The results also showed an up to 80% reduction in loss and up to 15% increase in accuracy for images with unseen distortions compared to the classical TL approach. This work improves classification results and increases robustness to distortions in a straightforward manner.

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: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.761
Threshold uncertainty score0.617

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 studies0.0010.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
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 head0.060
GPT teacher head0.245
Teacher spread0.185 · 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
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

Citations1
Published2022
Admission routes2
Has abstractyes

Explore more

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