I am currently a Ph.D. student at Clemson University, where I am working with Dr. Razi at the AI-based Sensing, Networking, and Data Services (AI-SENDS) Research Group. My research interests include Machine Learning, Computer Vision, Computational Imaging, Multiple-instance Learning, Time Series Analysis, and Information-theoretical Methods for AI, and Semantic Communication.

News

• [2024/8] Congrats! Our paper about data selection has been accepted by round 1 of WACV2025. The accepetance rate of round 1 is 12% (=167/1381).
• [2024/8] I am invited as ICLR2025 Reviewer.
• [2024/8] Congrats! Our paper about GNN for traffic network analysis has been accepted by Sigspatial2024 as Oral presentation.
• [2024/7] Congrats! Our paper DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification has been accepted by ECCV2024.
• [2024/6] Congrats! Our paper Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inference has been accepted by IEEE Trans. on Machine Learning in Communications and Networking.
• [2024/6] Congrats! Our paper SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation has been accepted by MICCAI2024.
• [2024/6] Congrats! Our paper Quantification of cardiac capillarization in basement-membrane-immunostained myocardial slices using Segment Anything Model has been accepted by Nature Scientific Reports.
• [2024/5] Congrats! Our paper TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning has been accepted by ICML2024.
• [2024/4] Congrats! Our paper Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters has been accepted by PBDL@CVPR2024 as Oral Presentation.
• [2024/4] Congrats! Our paper nnMobileNet: Rethinking CNN for Retinopathy Research has been accepted by DCAMI@CVPR2024.

Featured Papers (By interest)

Mulitple-Instance Learning

• Chen, X., Qiu, P., Zhu, W., Li, H., Wang, H., Sotiras, A., … & Razi, A. TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML2024). [Paper]

Computational Imaging, Digital Holography

• Chen, X., Zhu, W., Qiu, P., & Razi, A. (2024). Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters (PBDL@CVPR2024). [paper]
• Chen, X., Wang, H., Zhang, Z., Li, Z., Li, H., Ye, T., & Razi, A. (2024, March). Enhancing digital hologram reconstruction using reverse-attention loss for untrained physics-driven deep learning models with uncertain distance. In AI and Optical Data Sciences V (Vol. 12903, pp. 132-141). SPIE. [Paper] [Presentation]
• Chen, X., Wang, H., Razi, A., Kozicki, M., & Mann, C. (2023). DH-GAN: a physics-driven untrained generative adversarial network for holographic imaging. Optics Express, 31(6), 10114-10135. [paper]
• Li, H., Chen, X., Chi, Z., Mann, C., & Razi, A. (2020). Deep DIH: single-shot digital in-line holography reconstruction by deep learning. Ieee Access, 8, 202648-202659. [paper]

Determinatal Point Processing (DPP) in Applications

• Chen, X., Li, H., Amin, R., & Razi, A. (2024). RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples. arXiv preprint arXiv:2304.04137. [Paper] (Accepted by WACV2025)
• Chen, X., Li, H., Amin, R., & Razi, A. (2024). Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inference. [Paper] (Accepted by IEEE TMLCN)

Time Series Analysis

• Chen, X., Qiu, P., Zhu, W., Li, H., Wang, H., Sotiras, A., … & Razi, A. TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning (ICML2024). [Paper]
• Li, H., Carreon-Rascon, A. S., Chen, X., Yuan, G., & Li, A. (2024). MTS-LOF: medical time-series representation learning via occlusion-invariant features. IEEE Journal of Biomedical and Health Informatics. [Paper]

Medical Image Analysis

• Zhu, W., Qiu, P., Chen, X., Li, X., Lepore, N., Dumitrascu, O. M., & Wang, Y. nnMobileNet: Rethinking CNN for Retinopathy Research (DCAMI@CVPR2024). [Paper]
• Zhu, W., Chen, X., Qiu, P., Farazi, M., Sotiras, A., Razi, A., & Wang, Y. (2024). SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation. arXiv preprint arXiv:2406.14896. [Paper]
• Quantification of cardiac capillarization in basement-membrane-immunostained myocardial slices using Segment Anything Model — Zhang, Z., Chen, X., Richardson, W., Gao, B. Z., Razi, A., & Ye, T. (2023). Quantification of cardiac capillarization in single-immunostained myocardial slices using weakly supervised instance segmentation. arXiv preprint arXiv:2311.18173.