RISS 학술연구정보서비스

검색

인기 검색어

    다국어 입력

    http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

    변환된 중국어를 복사하여 사용하시면 됩니다.

    예시)
    • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
    • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
    닫기
    KCI등재

    아크페이스에 지식 증류를 적용한 얼굴인식 = Face Recognition with Knowledge Distillation on Arcface

    한글로보기

    https://www.riss.kr/link?id=A108686727

    • 0

      상세조회
    • 0

      다운로드
    서지정보 열기
    • 내보내기
    • 내책장담기
    • 공유하기
    • 오류접수

    부가정보

    다국어 초록 (Multilingual Abstract) kakao i 다국어 번역

    This paper studied the model lightening and speed improvement of face recognition. To this end, we propose a method of training with MobileNetV2 through knowledge distillation as a student model and based on ArcFace and ResNet50 as a teacher model. ArcFace is face recognition model using Additive Angular Margin Loss. The main objective was to compare the performance of the student model against that of the teacher model in terms of similarity results. The findings indicated that the student model outperformed the teacher model in terms of similarity results. These results suggest that the MobileNetV2-based student model can achieve comparable face recognition performance to the more complex ResNet50-based teacher model, while being computationally more efficient.
    번역하기

    This paper studied the model lightening and speed improvement of face recognition. To this end, we propose a method of training with MobileNetV2 through knowledge distillation as a student model and based on ArcFace and ResNet50 as a teacher model. Ar...

    This paper studied the model lightening and speed improvement of face recognition. To this end, we propose a method of training with MobileNetV2 through knowledge distillation as a student model and based on ArcFace and ResNet50 as a teacher model. ArcFace is face recognition model using Additive Angular Margin Loss. The main objective was to compare the performance of the student model against that of the teacher model in terms of similarity results. The findings indicated that the student model outperformed the teacher model in terms of similarity results. These results suggest that the MobileNetV2-based student model can achieve comparable face recognition performance to the more complex ResNet50-based teacher model, while being computationally more efficient.

    더보기

    참고문헌 (Reference)

    1 "The Aju-News Page"

    2 V. Thai, "Smart home Management System with Face Recognition based on ArcFace model in Deep Convolutional Neural Network" 3 (3): 754-761, 2022

    3 Y. Martindez-Díaz, "ShuffleFaceNet: A Lightweight Face Architecture for Efficient and Highly-Accurate Face Recognition" 2019

    4 류세열 ; 김혜진 ; 차경애, "ResNet을 이용한 얼굴 인식 기반 출입관리시스템 개발" 한국멀티미디어학회 22 (22): 823-831, 2019

    5 M. Sandler, "MobileNetV2 : Inverted Residuals and Linear Bottlenecks" 4510-4520, 2018

    6 S. Chen, "Mobile FaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices" 10996 : 428-438, 2018

    7 Y. Guo, "MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition" 87-102, 2016

    8 L. Wang, "Knowledge Distillation and Student-Teacher Learning for Visual Intelligence : A Review and New Outlooks" 6 (6): 3048-3068, 2022

    9 J. Gou, "Knowledge Distillation : A Survey" 129 (129): 1789-1819, 2021

    10 M. Alansari, "GhostFaceNets:Lightweight Face Recognition Model From Cheap Operations" 11 : 35429-35446, 2023

    1 "The Aju-News Page"

    2 V. Thai, "Smart home Management System with Face Recognition based on ArcFace model in Deep Convolutional Neural Network" 3 (3): 754-761, 2022

    3 Y. Martindez-Díaz, "ShuffleFaceNet: A Lightweight Face Architecture for Efficient and Highly-Accurate Face Recognition" 2019

    4 류세열 ; 김혜진 ; 차경애, "ResNet을 이용한 얼굴 인식 기반 출입관리시스템 개발" 한국멀티미디어학회 22 (22): 823-831, 2019

    5 M. Sandler, "MobileNetV2 : Inverted Residuals and Linear Bottlenecks" 4510-4520, 2018

    6 S. Chen, "Mobile FaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices" 10996 : 428-438, 2018

    7 Y. Guo, "MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition" 87-102, 2016

    8 L. Wang, "Knowledge Distillation and Student-Teacher Learning for Visual Intelligence : A Review and New Outlooks" 6 (6): 3048-3068, 2022

    9 J. Gou, "Knowledge Distillation : A Survey" 129 (129): 1789-1819, 2021

    10 M. Alansari, "GhostFaceNets:Lightweight Face Recognition Model From Cheap Operations" 11 : 35429-35446, 2023

    11 S. Sengupta, "Frontal to Profile Face Verification in the Wild" 1-9, 2016

    12 A. Asmara, "Face Recognition Using ArcFace and Face Net in Google Cloud Platform For Attendance System Mobile Application" (219) : 134-144, 2022

    13 G. Hinton, "Distilling the Knowledge in a Neural Network" 2014

    14 K. He, "Deep Residual Learning for Image Recognition" 770-778, 2016

    15 하영서 ; 박지희 ; 심재창, "CNN 모델과 샴 네트워크를 이용한 얼굴 인식 성능 비교" 한국멀티미디어학회 26 (26): 413-419, 2023

    16 J. Deng, "ArcFace:Additive Angular Margin Loss for Deep Face Recognition" 4685-4694, 2018

    더보기

    동일학술지(권/호) 다른 논문

    분석정보

    View

    상세정보조회

    0

    Usage

    원문다운로드

    0

    대출신청

    0

    복사신청

    0

    EDDS신청

    0

    동일 주제 내 활용도 TOP

    더보기

    주제

    연도별 연구동향

    연도별 활용동향

    연관논문

    연구자 네트워크맵

    공동연구자 (7)

    유사연구자 (20) 활용도상위20명

    이 자료와 함께 이용한 RISS 자료

    나만을 위한 추천자료

    해외이동버튼