[Open DMQA Seminar] Deep semi-supervised learning скачать в хорошем качестве

[Open DMQA Seminar] Deep semi-supervised learning

딥러닝은 컴퓨터 비전을 포함한 여러 다양한 분야에서 좋은 성능을 보이고 있다. 이 때, 딥러닝이 좋은 성능을 보이기 위해서는 다량의 레이블 데이터를 필요로 한다. 금일 세미나에서는 레이블 데이터 수에 크게 의존하는 딥러닝의 특성을 보완하고자 등장한 Semi-supervised learning (준지도학습)의 개념 및 예시, 그리고 최신 연구트렌드에 대해 소개하고자 한다. 참고 문헌: [1] Oliver, A., Odena, A., Raffel, C. A., Cubuk, E. D., & Goodfellow, I. (2018). Realistic evaluation of deep semi-supervised learning algorithms. In Advances in neural information processing systems (pp. 3235-3246). [2] Sajjadi, Mehdi, Mehran Javanmardi, and Tolga Tasdizen. "Regularization with stochastic transformations and perturbations for deep semi-supervised learning." Advances in neural information processing systems 29 (2016): 1163-1171. [3] Tarvainen, Antti, and Harri Valpola. "Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results." arXiv preprint arXiv:1703.01780 (2017). [4] Miyato, Takeru, et al. "Virtual adversarial training: a regularization method for supervised and semi-supervised learning." IEEE transactions on pattern analysis and machine intelligence 41.8 (2018): 1979-1993. [5] Laine, Samuli, and Timo Aila. "Temporal ensembling for semi-supervised learning." arXiv preprint arXiv:1610.02242 (2016). [6] Lee, Dong-Hyun. "Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks." Workshop on challenges in representation learning, ICML. Vol. 3. No. 2. 2013. [7] Guo, Lan-Zhe, et al. "Safe deep semi-supervised learning for unseen-class unlabeled data." International Conference on Machine Learning. PMLR, 2020. [8] Chen, Yanbei, et al. "Semi-supervised learning under class distribution mismatch." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34. No. 04. 2020.