Thesis Details

Hodnocení neurčitosti predikcí neuronových sítí v úlohách klasifikace, detekce a segmentace

Bachelor's Thesis Student: Vlasák Jiří Academic Year: 2021/2022 Supervisor: Herout Adam, prof. Ing., Ph.D.
English title
Assessment of Uncertainty of Neural Net Predictions in the Tasks of Classification, Detection and Segmentation
Language
Czech
Abstract

This work focuses on comparing three widely used methods for improving uncertainty estimations: Deep Ensembles, Monte Carlo Dropout, and Temperature Scaling. These methods are applied to six computer vision models that are pretrained as well as trained fromscratch. The models are then evaluated on computer vision datasets for classification, semantic segmentation, and object detection using a wide range of metrics. The models are also evaluated on distorted versions of these datasets to measure their performance on out-of-distribution data.     These modified models achieve promising results. Ensembles outperform the other models by as high as 70 % in accuracy and 0.2 in IOU on the distorted MedSeg COVID-19 segmentation dataset while also outperforming the other models on the CIFAR-100 and FMNIST datasets.

Keywords

monte carlo dropout, deep ensembles, temperature scaling, classification, semantic segmentation, object detection, dataset shift, model calibration, FMNIST, CIFAR-100, PASCAL-VOC

Department
Degree Programme
Files
Status
defended, grade A
Date
13 June 2022
Reviewer
Committee
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT), předseda
Beran Vítězslav, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Citation
VLASÁK, Jiří. Hodnocení neurčitosti predikcí neuronových sítí v úlohách klasifikace, detekce a segmentace. Brno, 2022. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2022-06-13. Supervised by Herout Adam. Available from: https://www.fit.vut.cz/study/thesis/25039/
BibTeX
@bachelorsthesis{FITBT25039,
    author = "Ji\v{r}\'{i} Vlas\'{a}k",
    type = "Bachelor's thesis",
    title = "Hodnocen\'{i} neur\v{c}itosti predikc\'{i} neuronov\'{y}ch s\'{i}t\'{i} v \'{u}loh\'{a}ch klasifikace, detekce a segmentace",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2022,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/25039/"
}
Back to top