Shuai Lu 陆帅
Postdoctoral Fellow
- Affiliation
- Beijing Institute of Technology
- Research
- Vision-Language Models · Anomaly Detection · Medical Image Analysis
- Address
- Beijing 100081, China
- lushuaie@gmail.com
Biography
Introduction
I am a postdoctoral fellow in the School of Information and Electronics at Beijing Institute of Technology (BIT), China. I received my Ph.D. degree in Electronic Information from BIT in 2024. From 2025 to 2026, I was a visiting scholar at the Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore, supported by the China Scholarship Council's Innovative Talents International Cooperation Program. My research focuses on artificial intelligence for medical and industrial applications, with particular interests in vision-language models, unsupervised anomaly detection, and ophthalmic image analysis.
News
- Completed my visiting scholar appointment at IHPC, A*STAR, Singapore.
- Our paper Dinomaly was published at CVPR 2025.
- Started a visiting scholar appointment at IHPC, A*STAR, Singapore.
- Joined Beijing Institute of Technology as a postdoctoral fellow.
- Received my Ph.D. degree in Electronic Information from Beijing Institute of Technology.
Journal Articles
9 publicationsDual-task teacher–student networks for unsupervised anomaly detection
Anomaly Detection for Medical Images using Heterogeneous Auto-Encoder
PKRT-Net: Prior knowledge-based relation transformer network for optic cup and disc segmentation
Encoder-Decoder Contrast for Unsupervised Anomaly Detection in Medical Images
PatchCL-AE: Anomaly Detection for Medical Images Using Patch-wise Contrastive Learning-based Auto-encoder
Mixed Maximum Loss Design for Optic Disc and Optic Cup Segmentation with Deep Learning from Imbalanced Samples
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis
Conference Papers
3 publicationsDinomaly: The less is more philosophy in multi-class unsupervised anomaly detection
ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction
DE-AE: A Dual-Encoder-Based Auto-encoder Framework with Improved Transformer for Anomaly Detection in Medical Imaging
Patents
4 records-
一种基于视觉语言模型的视盘萎缩弧弱监督分割方法
Invention patent · First inventor -
一种基于血管特征引导的视盘和视杯分割方法
CN115018855A · 2022-09-06 · Second inventor -
一种基于无监督异构蒸馏框架的视网膜 OCT 图像病变分类方法
CN116091449A · 2023-05-09 · Second inventor -
一种基于扭结点的轻量级视杯分割方法
Invention patent · Second inventor
Reviews
Conference Review
- Medical Image Computing and Computer Assisted Intervention (MICCAI)
- AAAI Conference on Artificial Intelligence (AAAI)
Journal Review
- IEEE Transactions on Image Processing (TIP)
- IEEE Journal of Biomedical and Health Informatics (JBHI)
- IEEE Transactions on Evolutionary Computation (TEVC)
- Engineering Applications of Artificial Intelligence
- Knowledge-Based Systems