Regularization using Noise samples Identified by the Feature norm for Face recognition
- 주제(키워드) Face recognition , Label noise , Feature norm , Regularization
- 주제(DDC) 006.31
- 발행기관 아주대학교 일반대학원
- 지도교수 Kyung-Ah Sohn
- 발행년도 2024
- 학위수여년월 2024. 2
- 학위명 석사
- 학과 및 전공 일반대학원 인공지능학과
- 실제URI http://www.dcollection.net/handler/ajou/000000033480
- 본문언어 영어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
Face recognition is a task that involves comparing two images of a face and determining whether they belong to the same person. Face recognition can be applied in a variety of environments, including surveillance systems. However, the performance of the deep learning model used for face recognition can be affected by the quality of the image. Therefore, recent studies on face recognition using deep learning have suggested taking image quality into consideration. Some studies have used feature norms, which is the L2 norm of extracted features from images using a deep learning model, to measure the image quality. However, previous studies have lacked analysis of why the feature norms correspond to image quality. This thesis presents a new hypothesis that a higher sample's feature norms indicate that the samples are similar to other samples learned by the deep learning model. We also demonstrate that this hypothesis can be used to distinguish noise samples. Additionally, we introduce a new regularization technique that uses noise samples to improve face recognition performance in low-resolution environments.
more목차
1. Introduction 1
2. Related Works 4
2.1. Face Recognition 4
2.2. Other Tasks using Feature Norm 5
3. Face Recognition 7
4. Feature Norm Analysis 10
5. Method 14
5.1. Noise Identifier 14
5.2. Noise Memory 15
5.3. Noise Direction Regularization (NDR) 15
6. Experiment 17
6.1. Experiment Setting 17
6.2. High-Quality Datasets 17
6.3. Low-Quality Datasets 18
6.4. Experiment Result 19
6.5. Visualization 21
7. Conclusion 23
Reference 24