Awards and Recognitions
CUTS: A Fully Unsupervised Framework for 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.
Liangbo L. Shen
Lucian V. Del Priore
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.