Learning Topological Representations for Deep Image Understanding

arXiv:2403.15361v1 Announce Type: cross
Abstract: In many scenarios, especially biomedical applications, the correct delineation of complex fine-scaled structures such as neurons, tissues, and vessels is critical for downstream analysis. Despite the strong predictive power of deep learning methods, they do not provide a satisfactory representation of these structures, thus creating significant barriers in scalable annotation and downstream analysis. In this dissertation, we tackle such challenges by proposing novel representations of these topological structures in a deep learning framework. We leverage …

abstract analysis applications arxiv biomedical cs.cv cs.lg deep learning image neurons power predictive representation type understanding