Lei Fan

Lei Fan (范磊)

PhD candidate at CSE, UNSW Syndey

lei.fan1 (at) unsw (dot) edu (dot) au

About Me

I’m currently third year PhD candidate at School of Computer Science and Engineering in The University of New South Wales (UNSW Sydney), co-supervised by A/Prof. Yang Song (opens new window), Prof. Arcot Sowmya (opens new window) and Prof. Erik Meijering (opens new window).

Research Interests. are in Deep Learning, Computer Vision, Biomedical Image Analysis, Agricultural Applications

(CVPR'22) GrainSpace: A Large-scale Dataset for Fine-grained and Domain-adaptive Recognition of Cereal Grains
- Lei Fan, Yiwen Ding., Yang Song et al
- We present a large-scale cereal grains dataset called GrainSpace, including a total of 5.25 million images determined by professional inspectors. The grain samples including wheat, maize and rice are collected from five countries and more than 30 regions.
- [Paper (opens new window)] [code&data (opens new window)]

(TMI'22 and MICCAI'21) Cancer Survival Prediction From Whole Slide Images With Self-Supervised Learning and Slide Consistency
- Lei Fan, Arcot Sowmya, Erik Meijering, Yang Song
- we propose a survival prediction model that exploits heterogeneous features at the patient-level. We introduce colorization as the pretext task to train the CNNs which are tailored for extracting features from patches of WSIs, and we develop a patient-level framework integrating multiple WSIs for survival prediction with consistency and ranking losses.
- [Paper-MICCAI21 (opens new window)], [Paper-TMI22 (opens new window)]
(MICCAI'22) Fast FF-to-FFPE Whole Slide Image Translation via Laplacian Pyramid and Contrastive Learning
- Lei Fan, Arcot Sowmya, Erik Meijering, Yang Song)
- we propose the fastFF2FFPE for translating FF into FFPE-style efficiently, and our model is based on the Laplacian Pyramid and contrastive learning.
- [Paper (opens new window)] [code (opens new window)]