Broadcasting and Media Magazine (방송과미디어)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지

영상 분류를 위한 준지도 학습 기법의 분류와 동작 원리의 이해

  • Published : 2022.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

본 고에서는 준지도 학습의 개념과 목표 그리고 대표 기법들의 동작 원리에 대해서 알아본다. 구체적으로, 영상 분류를 위한 준지도 학습 기법을 크게 label propagation 기반 기법과 representation learning 기반 기법으로 나누고, 이 두 가지 기법들의 특성을 분석하고, 대표 기법들의 동작 원리에 대해서 설명한다. 또한, 영상 분류 문제에서 위 두 가지 접근법들의 대표 기법들의 성능을 평가한다.

Keywords

Acknowledgement

성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임 (No. 2020R1C1C1009662, NRF-2020X1A3A109).

References

  1. J. H. Park, "Pseudo-labeling Technique for Image Classification with Limited Labeled Data," M.S. thesis, Dept. Multimedia Engineering, Dongguk University, Seoul, Republic of Korea, 2021, Available: http://lib.dongguk.edu/search/detail/CATTOT000001239284
  2. D.-H. Lee, "Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks," in Proc. Workshop Challenges Represent. Learn. (ICML), vol. 3, 2013. p. 2.
  3. Y. Grandvalet and Y. Bengio, "Semi-supervised learning by entropy minimization," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2004, pp. 529536.
  4. S. Laine and T. Aila, "Temporal ensembling for semi-supervised learning," in Proc. Int. Conf. Learn. Represent. (ICLR), 2017, pp. 113.
  5. T. Miyato, S.-I. Maeda, M. Koyama, and S. Ishii, "Virtual adversarial training: A regularization method for supervised and semisupervised learning," IEEE Trans. Pattern Anal. Mach. Intell., Vol. 41, No. 8, pp. 19791993, Aug 2019.
  6. M. Assran, M. Caron, I. Misra, P. Bojanowski, and A. Joulin, "Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples," arXiv preprint arXiv:2104.13963, 2021.
  7. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, "A Simple Framework for Contrastive Learning of Visual Representations," In International conference on machine learning. PMLR, 2020. pp. 1597-1607.
  8. J.-B. Grill et al., "Bootstrap Your Own Latent A New Approach to Self-Supervised Learning," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), Vancouver, Canada, 2020.
  9. A. Tarvainen and H. Valpola, "Mean teachers are better role models: Weight-averaged consistency targets improve semisupervised deep learning results," in Proc. Int. Conf. Learn. Represent. (ICLR), 2017, pp. 1-16.
  10. K. Sohn, D. Berthelot, C.-L. Li, Z. Zhang, N. Carlini, E. D. Cubuk, A. Kurakin, H. Zhang, and C. Raffel, "FixMatch: Simplifying semisupervised learning with consistency and confidence," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2020, pp. 1-21.
  11. D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. A. Raffel, "Mixmatch: A holistic approach to semisupervised learning," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2019, pp. 5050-5060.
  12. Q. Xie, Z. Dai, E. H. Hovy, M.-T. Luong, and Q. V. Le, "Unsupervised data augmentation for consistency training," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2020.
  13. H. Pham, Z. Dai, Q. Xie, and Q. V. Le, "Meta pseudo labels," In Proc. of the IEEE/CVF Conf. on Comput. Vis. and Pattern Recognit. (CVPR), 2021, pp. 11557-11568.
  14. T. Chen, S. Kornblith, K. Swersky, M. Norouzi, and G. Hinton, "Big Self-Supervised Models are Strong Semi-Supervised Learners," in Proc. Adv. Neural Inf. Process. Syst. (NIPS), Canada, 2020.
  15. A. Krizhevsky and G. Hinton, "Learning Multiple Layers of Features from Tiny Images," technical report, Univ. of Toronto, 2009.
  16. Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, and A. Y. Ng, "Reading digits in natural images with unsupervised feature learning," In NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
  17. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and F.-F. Li. ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, 2015.