Weicheng Dai

I am currently a phd student at Boston University, where I am very fortunately advised by Professor Kayhan Batmanghelich. Previously I worked at Yale University for Professor Julius Chapiro and Professor James S. Duncan. I also worked with Professor Chenyu You. I obtained a Master degree in Computer Science at New York University. My research interests include computer & medical vision, and explainable machine learning.

Email  /  LinkedIn  /  Github

In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation.

(* denotes equal contribution) Three simple principles: (1) tailness: giving more importance to tail class hard pixels; (2) consistency: enforcing the feature invariances to specified data transformations; (3) diversity: ensuring anatomical diversity in the set of different sampled images in those imbalanced, unlabeled, and diverse scenarios.

Two practical solutions via stratified group sampling theory that correct for the variance introduced by the common sampling practice, and achieve significant performance benefits.

In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation. We propose an adaptive supervised contrastive loss, where we compute the optimal locations of class centers uniformly distributed on the embedding space. We also use dynamic Tau to yield better separation between majority and minority classe.

In this work, we propose MORSE, a generic implicit neural rendering framework designed at an anatomical level to assist learning in medical image segmentation. The core of our approach is to formulate medical image segmentation as a rendering problem in an end-to-end manner.

In this work, we propose CFR, which focuses on exploring mitigating the reliance on spurious features for CLIP without using any group annotation. We showcase a lightweight representation calibration method for fine-tuning CLIP, by first generating a calibration set using the pretrained CLIP, and then calibrating representations of samples within this set through contrastive learning.