不确定性估计
(1)贝叶斯方法:
- Gal, Y., & Ghahramani, Z. (2016, June). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning (pp. 1050-1059). PMLR.(将Dropout看做贝叶斯近似的经典论文)
- Kendall, A., & Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision?. Advances in neural information processing systems, 30.(不确定性估计必读论文,将不确定性分为数据不确定性以及模型不确定性,并介绍了在分类和回归中不确定性估计的建模方法)
- Louizos, C., & Welling, M. (2017, July). Multiplicative normalizing flows for variational bayesian neural networks. In International Conference on Machine Learning (pp. 2218-2227). PMLR.(变分贝叶斯神经网络,EDL论文中的对比方法)
(2)集成方法:
-
- Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30.(集成方法的开山之作)
(3)证据深度学习:
-
-
- Sensoy, M., Kaplan, L., & Kandemir, M. (2018). Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems, 31.(证据分类)
- Sensoy, M., Kaplan, L., Cerutti, F., & Saleki, M. (2020, April). Uncertainty-aware deep classifiers using generative models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 04, pp. 5620-5627).(EDL作者的另一篇论文)
- Malinin, A., & Gales, M. (2018). Predictive uncertainty estimation via prior networks. Advances in neural information processing systems, 31.(使用狄利克雷分布建模不确定性的另一种方法)
- Ulmer, D. (2021). A survey on evidential deep learning for single-pass uncertainty estimation. arXiv preprint arXiv:2110.03051.(证据不确定性综述)
-
证据深度学习在医学图像分割中的应用
- Zou K, Yuan X, Shen X, et al. EvidenceCap: Towards trustworthy medical image segmentation via evidential identity cap[J]. arXiv preprint arXiv:2301.00349, 2023.
- Zou K, Yuan X, Shen X, et al. TBraTS: Trusted brain tumor segmentation[C]//Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part VIII. Cham: Springer Nature Switzerland, 2022: 503-513.(可信的脑肿瘤分割)
mbd.pub/o/GeBENHAGEN
擅长现代信号处理(改进小波分析系列,改进变分模态分解,改进经验小波变换,改进辛几何模态分解等等),改进机器学习,改进深度学习,机械故障诊断,改进时间序列分析(金融信号,心电信号,振动信号等)