본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

고급검색

인명/단체명

저자정보 상세정보
인명/단체명을 입력하세요.

키워드

  • 대표어

  • 외국어

-

초록보기

In supervised learning, labeling of all data is essential, and in particular, in the case of object detection, all objects belonging to the image and to be learned have to be labeled. Due to this problem, continual learning has recently attracted attention, which is a way to accumulate previous learned knowledge and minimize catastrophic forgetting. In this study, a continaul learning model is proposed that accumulates previously learned knowledge and enables learning about new objects. The proposed method is applied to CenterNet, which is a object detection model of anchor-free manner. In our study, the model is applied the knowledge distillation algorithm to be enabled continual learning. In particular, it is assumed that all output layers of the model have to be distilled in order to be most effective. Compared to LWF, the proposed method is increased by 23.3%p mAP in 19+1 scenarios, and also rised by 28.8%p in 15+5 scenarios.

In supervised learning, labeling of all data is essential, and in particular, in the case of object detection, all objects belonging to the image and to be learned have to be labeled. Due to this problem, continual learning has recently attracted attention, which is a way to accumulate previous learned knowledge and minimize catastrophic forgetting. In this study, a continaul learning model is proposed that accumulates previously learned knowledge and enables learning about new objects. The proposed method is applied to CenterNet, which is a object detection model of anchor-free manner. In our study, the model is applied the knowledge distillation algorithm to be enabled continual learning. In particular, it is assumed that all output layers of the model have to be distilled in order to be most effective. Compared to LWF, the proposed method is increased by 23.3%p mAP in 19+1 scenarios, and also rised by 28.8%p in 15+5 scenarios.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
화물 선적 최적화를 위한 LiDar 센서 기반 비규격 화물 체적산출 방법 연구 = A study on the method of non-standard cargo volume calculation based on LiDar sensor for cargo loading optimization 전영준, 김예슬, 안선규, 정석찬 p. 559-567
방향 정규화 및 CNN 딥러닝 기반 차량 번호판 인식에 관한 연구 = A study on the license plate recognition based on direction normalization and CNN deep learning 기재원, 조성원 p. 568-574
Skeleton 정보와 LSTM을 이용한 작업자 동작인식 = Motion recognition of workers using skeleton and LSTM 전왕수, 이상용 p. 575-582
임베디드 보드에서 영상 처리 및 딥러닝 기법을 혼용한 돼지 탐지 정확도 개선 = Accuracy improvement of pig detection using image processing and deep learning techniques on an embedded board 유승현, 손승욱, 안한세, 이세준, 백화평, 정용화, 박대희 p. 583-599
Knowledge Distillation 계층 변화에 따른 Anchor Free 물체 검출 Continual Learning = Anchor free object detection continual learning according to knowledge distillation layer changes 강수명, 정대원, 이준재 p. 600-609
IoT 기반의 스마트 마스크 설계 및 구현 = Design and implementation of smart mask based on IoT 왕이, 김현기 p. 610-619
애니메이션의 샷밀도 몽타주 패턴 = The shot density montage pattern for annimation 신연우 p. 620-627
소셜 미디어 사용자가 제작한 광고 효과 : A study on the effectiveness of video advertisements generated by social media users : centered on information and entertainment video comparison / 정보형과 오락형 동영상 비교를 중심으로 장녕, 추장운, 김치용 p. 628-639
폐경기 여성을 대상으로 제공하는 디지털 기반 운동 치료 = Study on digital-based exercise therapy for menopausal women : 서비스 디자인 제안 박채은, 강현민, 서석교, 전용관, 김진우 p. 640-648
(A) study on the cognitive potential of pre-school children with AR collaborative TUI Qianrong Deng, Dong-min Cho p. 649-659

참고문헌 (14건) : 자료제공( 네이버학술정보 )

참고문헌 목록에 대한 테이블로 번호, 참고문헌, 국회도서관 소장유무로 구성되어 있습니다.
번호 참고문헌 국회도서관 소장유무
1 S. Gang, D. Chung, and J.J. Lee, “Knowledge Distillation Based Continual Learning for PCB Part Detection,” Journal of Korea Multimedia Society, Vol. 24, No. 7, pp. 868-879, 2021. 미소장
2 Z. Chen and B. Liu, “Lifelong Machine Learning,”Synthesis Lectures on Artificial Intelligence and Machine Learning, Vol. 12, No. 3, pp. 1-207, 2018. 미소장
3 G. Hinton, O. Vinyals, and J. Dean, “Distilling the Knowledge in a Neural Network Geoffrey,”arXiv Preprint, arXiv:1503.02531, 2015. 미소장
4 C. Peng, K. Zhao, S. Maksoud, M. Li, and B. C. Lovell, “SID: Incremental Learning for Anchor-free Object Detection via Selective and Inter-related Distillation,” Computer Vision and Image Understanding, Vol. 210, 103229, pp. 1-8, 2021. 미소장
5 H. Yoon and J. Lee, “PCB Component Classification Algorithm Based on YOLO Network for PCB Inspection,” Journal of Korea Multimedia Society, Vol. 24, No. 8, pp. 988-999, 2021. 미소장
6 X. Zhou, D. Wang, and P. Krähenbühl, “Objects as Points,” arXiv Preprint, arXiv:1904.07850, 2019. 미소장
7 M. Masana, X. Liu, B. Twardowski, M. Menta, A.D. Bagdanov, and J. van de Weijer, “Classincremental Learning: Survey and Per-formance Evaluation on Image Classification,”arXiv Preprint, arXiv:2010.15277, pp. 1-26, 2020. 미소장
8 Z. Li and D. Hoiem, “Learning without Forgetting,”IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 40, No. 12, pp. 2935-2947, 2017. 미소장
9 U. Michieli and P. Zanuttigh, “Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1114-1124, 2021. 미소장
10 K. Shmelkov, C. Schmid, and K. Alahari, “Incremental Learning of Object Detectors without Catastrophic Forgetting,” Proceedings of the IEEE International Conference on Computer Vision, pp. 3420- 3429, 2017. 미소장
11 Z. Tian, C. Shen, H. Chen, and T. He, “FCOS:A Simple and Strong Anchor-free Object Detector,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, Issue 4, pp. 1922-1933, 2020. 미소장
12 U. Michieli and P. Zanuttigh, “Incremental Learning Techniques for Semantic Segmentation,”Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 1-8, 2019. 미소장
13 U. Michieli and P. Zanuttigh, “Knowledge Distillation for Incremental Learning in Semantic Segmentation,” Computer Vision and Image Understanding, Vol. 205, 103167, pp.1-16, 2021. 미소장
14 GitHub - xingyizhou/CenterNet: Object detection, 3D detection, and pose estimation using center point detection, https://github.com/xingyizhou/CenterNet (accessed Oct. 24, 2021). 미소장

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차

권호

기사명 원문보기 기사목차
닫기