Publication:

Evolutionary Multi-Objective Calibration of MC-Dropout Predictive Uncertainty Quantification for Diabetic Retinopathy

Date

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0000-0002-5145-872X
cris.virtualsource.departmenta6e15b57-cd91-48e5-9630-242b1b7129de
cris.virtualsource.orcida6e15b57-cd91-48e5-9630-242b1b7129de
dc.contributor.authorAbreu-Cardenas, Miguel
dc.contributor.authorCalderon-Ramirez, Saul
dc.contributor.authorRojas Gonzalez, Sebastian
dc.date.accessioned2026-11-16T14:14:48Z
dc.date.available2026-11-16T14:14:48Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractMonte carlo dropout is one of the most widely used methods for uncertainty quantification in deep learning, yet practitioners often rely on fixed heuristic settings for parameters such as the dropout rate and the ensemble size. Therefore, in this work, we formulate the joint tuning of dropout rate p, temperature T, and sample count N as a multi-objective optimisation problem that minimises expected calibration error and computational cost subject to an accuracy-retention constraint. We solve this problem with non-dominated sorting genetic algorithm II and reference vector guided evolutionary algorithm across three architectures—DenseNet121, MobileViT, and TinyViT—for binary diabetic retinopathy classification. Two main findings emerge, (1) calibration gains saturate at low sample counts (N≈10), enabling a 3× reduction in inference cost relative to common heuristics; and (2) optimal dropout rates are strongly architecture-dependent, with convolutional neural networks tolerating moderate perturbation (p≈0.4) while vision transformers require substantially lower rates (p≈0.1), challenging the widespread use of fixed Monte carlo dropout configurations. These findings demonstrate that evolutionary multi-objective optimisation can efficiently navigate the cost-calibration trade-off for uncertainty quantification in medical imaging.
dc.description.wosFundingTextComputational support was provided by the Kabre supercomputer at the National High Technology Center of Costa Rica (CeNAT). Sebastian Rojas Gonzalez acknowledges support by FWO Belgium (grant 1216021N).
dc.identifier.doi10.1145/3795101.3805423
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60814
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherASSOC COMPUTING MACHINERY
dc.source.beginpage253
dc.source.conferenceGenetic and Evolutionary Computation Conference Companion - GECCO
dc.source.conferencedate2026-07-13
dc.source.conferencelocationSan Jose, Costa Rica
dc.source.endpage256
dc.source.journalPROCEEDINGS OF THE 2026 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, GECCO 2026 COMPANION
dc.source.numberofpages4
dc.title

Evolutionary Multi-Objective Calibration of MC-Dropout Predictive Uncertainty Quantification for Diabetic Retinopathy

dc.typeProceedings paper
dspace.entity.typePublication
imec.internal.crawledAt2026-11-14
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-14
Files

Original bundle

Name:
3795101.3805423.pdf
Size:
818.96 KB
Format:
Adobe Portable Document Format
Description:
Published
Publication available in collections: