2021
Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations
NeurIPS 2021poster
We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. We show that models that capture implicit hierarchical relationships between subvolumes are better suited for this task. To that end, we consider encoder-decoder architectures with a hyp…