MétaCan
Menu
Back to cohort
Record W2911290743 · doi:10.1073/pnas.1907377117

On instabilities of deep learning in image reconstruction and the potential costs of AI

2020· article· en· W2911290743 on OpenAlexafffund
Vegard Antun, Francesco Renna, Clarice Poon, Ben Adcock, Anders C. Hansen

Bibliographic record

VenueProceedings of the National Academy of Sciences · 2020
Typearticle
Languageen
FieldMedicine
TopicMedical Imaging Techniques and Applications
Canadian institutionsSimon Fraser University
FundersFundação para a Ciência e a TecnologiaNatural Sciences and Engineering Research Council of CanadaEuropean CommissionResearch Councils UKRoyal SocietyEngineering and Physical Sciences Research CouncilCanadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of CanadaLeverhulme TrustNvidia
KeywordsCounterintuitiveDeep learningArtificial intelligenceComputer scienceImage (mathematics)InstabilityStability (learning theory)Iterative reconstructionField (mathematics)Sampling (signal processing)Computer visionMachine learningMathematicsPhysics

Abstract

fetched live from OpenAlex

Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper, we demonstrate a crucial phenomenon: Deep learning typically yields unstable methods for image reconstruction. The instabilities usually occur in several forms: 1) Certain tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction; 2) a small structural change, for example, a tumor, may not be captured in the reconstructed image; and 3) (a counterintuitive type of instability) more samples may yield poorer performance. Our stability test with algorithms and easy-to-use software detects the instability phenomena. The test is aimed at researchers, to test their networks for instabilities, and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning 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)0.008
metaresearch head score (Gemma)0.073
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 score0.009
Threshold uncertainty score0.043

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.073
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.007
Scholarly communication0.0030.011
Open science0.0020.005
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0090.001

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 head0.023
GPT teacher head0.312
Teacher spread0.289 · 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

Citations759
Published2020
Admission routes2
Has abstractyes

Explore more

Same venueProceedings of the National Academy of SciencesSame topicMedical Imaging Techniques and ApplicationsFrench-language works237,207