$\require{mediawiki-texvc}$

연합인증

연합인증 가입 기관의 연구자들은 소속기관의 인증정보(ID와 암호)를 이용해 다른 대학, 연구기관, 서비스 공급자의 다양한 온라인 자원과 연구 데이터를 이용할 수 있습니다.

이는 여행자가 자국에서 발행 받은 여권으로 세계 각국을 자유롭게 여행할 수 있는 것과 같습니다.

연합인증으로 이용이 가능한 서비스는 NTIS, DataON, Edison, Kafe, Webinar 등이 있습니다.

한번의 인증절차만으로 연합인증 가입 서비스에 추가 로그인 없이 이용이 가능합니다.

다만, 연합인증을 위해서는 최초 1회만 인증 절차가 필요합니다. (회원이 아닐 경우 회원 가입이 필요합니다.)

연합인증 절차는 다음과 같습니다.

최초이용시에는
ScienceON에 로그인 → 연합인증 서비스 접속 → 로그인 (본인 확인 또는 회원가입) → 서비스 이용

그 이후에는
ScienceON 로그인 → 연합인증 서비스 접속 → 서비스 이용

연합인증을 활용하시면 KISTI가 제공하는 다양한 서비스를 편리하게 이용하실 수 있습니다.

딥 러닝에서 Labeling 부담을 줄이기 위한 연구분석
An Analysis of the methods to alleviate the cost of data labeling in Deep learning 원문보기

Journal of the convergence on culture technology : JCCT = 문화기술의 융합, v.8 no.1, 2022년, pp.545 - 550  

한석민 (한국교통대학교 데이터사이언스전공)

초록
AI-Helper 아이콘AI-Helper

딥러닝은 많은 데이터를 필요로 한다는 것은 이미 널리 알려져있다. 이를 통해, 딥러닝에 쓰이는 신경망의 수없이 많은 parameter들을 학습시킨다. 학습과정에는 데이터뿐 아니라, 각 데이터별로 전문가가 입력한 label이 필요한 경우가 대부분인데, 이 label을 얻는 과정은 시간과 자원 소비가 심하다. 이 문제를 완화하기 위해, few-shot learning, self-supervised learning, weak-supervised learning등이 연구되어오고 있다. 본 논문에서는, label을 상대적으로 적은 노력으로 수행하기 위한 연구들의 동향을 살펴보고, 앞으로의 개선 방향을 제시하도록 한다.

Abstract ▼ AI-Helper 아이콘AI-Helper

In Deep Learning method, it is well known that it requires large amount of data to train the deep neural network. And it also requires the labeling of each data to fully train the neural network, which means that experts should spend lots of time to provide the labeling. To alleviate the problem of ...

주제어

#딥 러닝   #유사성   #불확실성   #라벨링  

표/그림 (5)

참고문헌 (31)

  1. Phil-Joo Moon, "Analysis of Deep Learning Methods for Classification and Detection of Malware," International Journal of Advanced Culture Technology Vol.9 No.3 291-297 (2021). https://doi.org/10.17703/IJACT.2021.9.3.291 

    원문보기 상세보기 crossref

  2. Weol-Youg. Kim, Seung-Jung. Shin, "Large orchard apple classification system,"The Journal of the Convergence on Culture Technology (JCCT), Vol. 4, No. 4, pp.393-399, November 30, 2018. https://doi.org/10.17703/JCCT.2018.4.4.393 

    원문보기 상세보기 crossref

  3. M. Abe, K. Nakagawa,"Cross-sectional Stock Price Prediction using Deep Learning for Actual Investment Management,"Proceedings of the 2020 Asia Service Sciences and Software Engineering Conference, May 2020, https://doi.org/10.1145/3399871.3399889 

    crossref

  4. G. Koch R. Zemel, R. Salakhutdinov, "Siamese Neural Networks for One-shot Image Recognition," Proceedings of the 32nd International Conference on Machine Learning, Lille, France, 2015. 

  5. O. Vinyals, et al, "Matching Networks for One Shot Learning," 30th Conference on Neural Information Processing Systems (NIPS 2016), 2016. 

  6. J. Snell, K. Swersky, R.S. Zemel, "Jake Snell, Kevin Swersky, Richard S. Zemel,"Conference on Neural Information Processing Systems (NIPS 2017),2017. 

  7. A. Dosovitskiy, et al, "Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks," Conference on Neural Information Processing Systems (NIPS 2014), 2014. 

  8. I. Misra, L. Maaten, "Self-Supervised Learning of Pretext-Invariant Representations," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 

  9. S. Gidaris, P. Singh, N. Komodakis, "Unsupervised Representation Learning by Predicting Image Rotations," The proceedings of International Conference on Learning Representations(ICLR 2018), 2018. 

  10. T. Chen, S. Kornblith, Mo. Norouzi, G. Hinton, "A Simple Framework for Contrastive Learning of Visual Representations," The proceedings of International Conference on Machine Learning (ICML 2020), 2020. 

  11. K. He, et al, "Momentum Contrast for Unsupervised Visual Representation Learning," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 

  12. B. Bozorgtabar. et al, "Informative sample generation using class aware generative adversarial networks for classification of chest Xrays," Computer Vision and Image Understanding 184(1), 2019. https://doi.org/10.1016/j.cviu.2019.04.007 

    상세보기 crossref

  13. H. Zhen, et al,, Biomedical "Image Segmentation via Representative Annotation," Proceedings of the AAAI Conference on Artificial Intelligence , vol. 33, pp.5901-5908, 2019. 

  14. S. Mo, et al, "Mining GOLD Samples for Conditional GANs," Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp.6170-6181, 2019. 

  15. D. Mahapatra, et al, "Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network," MICCAI 2018. Lecture Notes in Computer Science, vol 11071. 2018. 

  16. C. Mayer,, R Timofte., "Adversarial Sampling for Active Learning," 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020. 

  17. Y. Gal, R. Islam, N., Z. Ghahramani, "Deep Bayesian Active Learning with Image Data," Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1183-1192, 2017. 

  18. M. Gorriz, et al, "Cost-Effective Active Learning for Melanoma Segmentation," the proceedings of NIPS 2017 workshop, 2017. 

  19. J. Dolz, et al, "Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation," Computerized Medical Imaging and Graphics, Vol 79, January 2020. https://doi.org/10.1016/j.compmedimag.2019.101660 

    상세보기 crossref

  20. R. Shen, et al, "Breast mass detection from the digitized X-ray mammograms based on the combination of deep active learning and self-paced learning," Future Generation Computer Systems, 2019. https://doi.org/10.1016/j.future.2019.07.013 

    상세보기 crossref

  21. C. Dai, et al, "Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling," The proceeding of MICCAI 2020, 2020, pp.156-165. 

  22. L. Yang, et al, "Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation," Lecture Notes in Computer Science, 2017. https://doi.org/10.1007/978-3-319-66179-7_46 

    crossref

  23. Y. Geifman, and R.Elyaniv, "Deep Active Learning over the Long Tail," arXiv: Learning, 2017. 

  24. C. Yin, et al, "Deep Similarity-Based Batch Mode Active Learning with Exploration-Exploitation," The proceeding of 2017 IEEE International Conference on Data Mining (ICDM), pp.575-584, 2017. 

  25. J., T. Ash, et al, "Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds," The proceedings of ICLR 2020 Conference, 2020. 

  26. X. Du, ,et al, "Building an Active Palmprint Recognition System," The proceedings of The International Conference on Image Processing, ICIP 2019, Taipei, Taiwan, pp.1685-1689, 2019. 

  27. D. Gissin, S. Shalevshwartz., "Discriminative Active Learning," arXiv: Learning, 2018. 

  28. A. Kirsch, et al, "BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning," Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp.7026-7037, 2019. 

  29. F. Zhdanov, "Diverse mini-batch Active Learning," arXiv: Learning, 2019. 

  30. R. Pinsler, et al, "Bayesian Batch Active Learning as Sparse Subset Approximation," Proceedings of the 33rd International Conference on Neural Information Processing Systems, 2019. 

  31. S. Han, "Analysis of Suggestive Learning in Deep Learning," The papers of Korea National University of Transportation, 2021. 

저자의 다른 논문 :

관련 콘텐츠

오픈액세스(OA) 유형

GOLD

오픈액세스 학술지에 출판된 논문

섹션별 컨텐츠 바로가기

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

AI-Helper 아이콘
AI-Helper
안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

선택된 텍스트

맨위로