A Differentiable Topological Notion of Local Maxima for Keypoint Detection

Abstract

In computer vision, keypoint detection is a fundamental task, with applications spanning from robotics to image retrieval; however, existing learning-based methods suffer from scale dependency and lack flexibility. This paper introduces a novel approach that leverages Morse theory and persistent homology, powerful tools rooted in algebraic topology. We propose a novel loss function based on the recent introduction of a notion of subgradient in persistent homology which achieves competitive performance in keypoint repeatability and introduces a principled and theoretically robust approach to the problem.

Cite

Text

Barbarani et al. "A Differentiable Topological Notion of Local Maxima for Keypoint Detection." ICML 2024 Workshops: Differentiable_Almost_Everything, 2024.

Markdown

[Barbarani et al. "A Differentiable Topological Notion of Local Maxima for Keypoint Detection." ICML 2024 Workshops: Differentiable_Almost_Everything, 2024.](https://mlanthology.org/icmlw/2024/barbarani2024icmlw-differentiable/)

BibTeX

@inproceedings{barbarani2024icmlw-differentiable,
  title     = {{A Differentiable Topological Notion of Local Maxima for Keypoint Detection}},
  author    = {Barbarani, Giovanni and Vaccarino, Francesco and Trivigno, Gabriele and Guerra, Marco and Berton, Gabriele and Masone, Carlo},
  booktitle = {ICML 2024 Workshops: Differentiable_Almost_Everything},
  year      = {2024},
  url       = {https://mlanthology.org/icmlw/2024/barbarani2024icmlw-differentiable/}
}