PI-Net: A Deep Learning Approach to Extract Topological Persistence Images

5 Jun 2019Anirudh SomHongjun ChoiKarthikeyan Natesan RamamurthyMatthew BumanPavan Turaga

Topological features such as persistence diagrams and their functional approximations like persistence images (PIs) have been showing substantial promise for machine learning and computer vision applications. Key bottlenecks to their large scale adoption are computational expenditure and difficulty in incorporating them in a differentiable architecture... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.