Chen Liu
Chen Liu
Home
News
Awards and Recognitions
Service
Experience
Publications
Contact
Light
Dark
Automatic
3
CUTS: A Framework for Multigranular Unsupervised Medical Image Segmentation
We developed a fully unsupervised framework for image segmentation and investigated its performance on natural images and more importantly, two medical image datasets. The proposed framework combines intra-image contrastive learning and local patch reconstruction to jointly learn a structured latent space. Then, it coarse-grains the latent pixel-level embeddings into a series of coarse-to-fine segmentations at various levels of granularity. The proposed method is end-to-end unsupervised and outperforms existing unsupervised segmentation methods in our quantitative experiments.
Chen Liu
,
Matthew Amodio
,
Liangbo L. Shen
,
Feng Gao
,
Arman Avesta
,
Sanjay Aneja
,
Jay Wang
,
Lucian V. Del Priore
,
Smita Krishnaswamy
Adversarial Focal Loss: Asking Your Discriminator for Hard Examples
We proposed a generalizable adaptation of Focal Loss to keypoint detection leveraging difficulty scores from a discriminator.
Chen Liu
,
Xiaomeng Dong
,
Michael Potter
,
Hsi-Ming Chang
,
Ravi Soni
Cite
×