Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through neural networks. But existing approaches in the differentiable particle filter framework do not admit valid probability densities in constructing measurement models, leading to incorrect quantification of the measurement uncertainty given state information. We propose to learn expressive and valid probability densities in measurement models through conditional normalizing flows, to capture the complex likelihood of measurements given states. We show that the proposed approach leads to improved estimation performance and faster training convergence in a visual tracking experiment.
School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院);State Key Laboratory of Submarine Geoscience, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学海洋地质国家重点实验室、自动化与智能传感学院)
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
Institute of Nanotechnology, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院纳米技术研究所);Institute of Theoretical Informatics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院理论信息学研究所)
Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows
Department of Computer Science Norwegian University of Science and Technology(挪威科学技术大学计算机科学系);BCAM – Basque Center for Applied Mathematics University of Coimbra, CISUC/LASI, DEI(巴斯克应用数学中心,科英布拉大学,CISUC/LASI,DEI);IKERBASQUE — Basque Foundation for Science(巴斯克科学基金会)
Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp EEG based on Conditional Normalizing Flow
School of Artificial Intelligence, Chongqing University of Technology(重庆理工大学人工智能学院);School of Smart Health, Chongqing Polytechnic University of Electronic Technology(重庆电子工程职业大学智能健康学院)
Dual Conditional Diffusion Models for Sequential Recommendation
The University of New South Wales(新南威尔士大学);Adobe Research(奥多比研究院);University of Technology Sydney(悉尼科技大学);University of California San Diego(加利福尼亚大学圣迭戈分校)