Dr Xiongjie Chen


Postdoctoral Researcher
B.Sc, M.Eng, PhD

About

Areas of specialism

Statistical machine learning; Bayesian inference; Monte Carlo sampling; Uncertainty quantification; AI in dentistry

Research

Research interests

Research projects

Teaching

Publications

Highlights

An up-to-date list of my publications can be found on my Google Scholar profile.

Xiongjie Chen, Yunpeng Li, Yongxin Yang (2023)Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)pp. 1-5 IEEE

Out-of-distribution (OOD) detection has recently received much attention from the machine learning community because it is important for deploying machine learning models in real-world applications. In this paper we propose an uncertainty quantification approach by modeling data distributions in feature spaces. We further incorporate an efficient ensemble mechanism, namely batch-ensemble, to construct the batch-ensemble stochastic neural networks (BE-SNNs) and overcome the feature collapse problem. We compare the performance of the proposed BE-SNNs with the other state-of-the-art approaches and show that BE-SNNs yield superior performance on several OOD detection benchmarks, such as the Two-Moons dataset, the FashionMNIST vs MNIST dataset, Fashion-MNIST vs NotMNIST dataset, and the CIFAR10 vs SVHN dataset.

Xiongjie Chen, Yunpeng Li (2022)Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flow, In: 2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022)pp. 782-786 IEEE

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.

Wenhan Li, Xiongjie Chen, Wenwu Wang, Victor Elvira, Yunpeng Li (2023)Differentiable Bootstrap Particle Filters for Regime-Switching Models, In: 2023 IEEE Statistical Signal Processing Workshop (SSP)2023-pp. 200-204 IEEE

Differentiable particle filters are an emerging class of particle filtering methods that use neural networks to construct and learn parametric state-space models. In real-world applications, both the state dynamics and measurements can switch between a set of candidate models. For instance, in target tracking, vehicles can idle, move through traffic, or cruise on motorways, and measurements are collected in different geographical or weather conditions. This paper proposes a new differentiable particle filter for regime-switching state-space models. The method can learn a set of unknown candidate dynamic and measurement models and track the state posteriors. We evaluate the performance of the novel algorithm in relevant models, showing its great performance compared to other competitive algorithms.