Publications

Detailed Information

Ensemble Methods for Image Classification : 이미지 분류를 위한 앙상블 방법

DC Field Value Language
dc.contributor.advisor박병욱-
dc.contributor.author한영준-
dc.date.accessioned2019-10-18T18:21:31Z-
dc.date.available2019-10-18T18:21:31Z-
dc.date.issued2019-08-
dc.identifier.other000000157884-
dc.identifier.urihttps://hdl.handle.net/10371/161658-
dc.identifier.urihttp://dcollection.snu.ac.kr/common/orgView/000000157884ko_KR
dc.description학위논문(석사)--서울대학교 대학원 :자연과학대학 통계학과,2019. 8. 박병욱.-
dc.description.abstractIn this paper, Deep Convolutional Neural Network (CNN) with various structures and loss functions are verified. Our data is VGGFace2 which is widely spread datasets. Using CNN models like VGG and ResNet, with cross entropy, cosface loss, and arcface loss, verify performance each models at first. Later, we use stacking method for ensemble. Also, unlike any other Face image classification problem, we used face detection to improve performance. So, First, do face detection so that we can focus only on each persons identity. Second, using face image, construct convolution layers. And then the last, gather all convolution neural network results and summarize them. Focusing on model structures and tunning procedures, we verify that the performance of model with ensemble get better than without ensemble.-
dc.description.abstract본 논문에서는 다양한 구조와 손실 함수를 갖는 합성곱 신경망을 검증한다. VGGFace2 데이터를 이용하여 교차 엔트로피, Cosine 손실 및 Arcface 손실과 함께 VGG 및 ResNet과 같은 합성곱 신경망 모델을 사용하여 각 모델의 성능을 검증한다. 또한 앙상블을 위해 스태킹을 사용한다. 알고리즘은 먼저 얼굴 인식을 수행하여 각 사람의 신원에만 집중할 수있게 하여 기존 얼굴 이미지 분류 문제와 달리 얼굴 검색을 사용하여 성능을 향상 시켰다. 그리고 얼굴 이미지를 사용하여 합성곱 신경망을 구성 한다. 마지막으로 모든 신경망 결과를 수집하고 앙상블하여 모델을 검증한다. 본 논문은 모델 구조와 무작위 검색을 통한 튜닝 절차에 중점을 두었으며, 앙상블을 통하여 기존 모델의 성능이 향상됨을 확인하였다.-
dc.description.tableofcontents1 Introduction 1
2 Model Structures 4
2.1 Baseline models . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.2 Structured models . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.3 Loss functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.4 Stacking . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3 Data 10
3.1 Data collecting . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2 Data preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . 11
4 Simulation and Evaluation 13
4.1 Training methods . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4.2 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5 Discussion 18
References 21
국문초록 24

List of Figures
3.1 Extracted face on VGGFace2 dataset on the same identity . . . 12
4.1 Training loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
5.1 Non-normalized plot . . . . . . . . . . . . . . . . . . . . . . . . 19
5.2 Normalized plot on training . . . . . . . . . . . . . . . . . . . . 20

List of Tables
4.1 Tuning hyperparameters . . . . . . . . . . . . . . . . . . . . . . 16
4.2 Tuning result . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.3 Stacking result . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
-
dc.language.isoeng-
dc.publisher서울대학교 대학원-
dc.subjectConvolutional Neural Network-
dc.subjectVGGFace2-
dc.subjectLoss functions-
dc.subjectStacking-
dc.subject.ddc519.5-
dc.titleEnsemble Methods for Image Classification-
dc.title.alternative이미지 분류를 위한 앙상블 방법-
dc.typeThesis-
dc.typeDissertation-
dc.contributor.AlternativeAuthorYeongjun Han-
dc.contributor.department자연과학대학 통계학과-
dc.description.degreeMaster-
dc.date.awarded2019-08-
dc.contributor.major통계학-
dc.identifier.uciI804:11032-000000157884-
dc.identifier.holdings000000000040▲000000000041▲000000157884▲-
Appears in Collections:
Files in This Item:

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share