arXiv Machine Learning
Sparse cubical complexes for efficient topology-preservation in image data
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Jun 30
TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
arXiv:2606. 29763v1 Announce Type: cross Abstract: Topological data analysis (TDA), particularly persistent homology (PH), captures geometric structural properties in medical images (e.
arXiv Machine Learning
Jun 18
Unreduced Persistence Diagrams for Topological Machine Learning
arXiv:2507. 07156v2 Announce Type: replace-cross Abstract: Supervised machine learning pipelines trained on features derived from persistent homology have been experimentally observed to ignore much of the information contained in a persistence diagram.
arXiv Machine Learning
Jul 22
Topology-Driven Clustering: Enhancing Performance with Betti Number Filtration
arXiv:2505. 04346v2 Announce Type: replace Abstract: Clustering aims at partitioning data points into groups of similar objects without knowing about the class labels.
arXiv Machine Learning
Jun 17
Non-negative Matrix Factorisation with Topological Regularisation
arXiv:2606. 17531v1 Announce Type: new Abstract: We investigate the learning of interpretable bases in non-negative matrix factorisation (NMF) by regularising the topology of the learned basis functions.
arXiv Machine Learning
Jun 16
Analytic Torsion and Spectral Gap Capture Persistent-Laplacian Performance
arXiv:2606. 16990v1 Announce Type: new Abstract: While persistent Laplacians (PL) offer a richer geometric representation of data than persistent homology, utilizing their full eigenspectrum for learning tasks is often hampered by high dimensionality and the ``varying length'' problem across different filtration scales.
arXiv AI
Jun 29
Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation
arXiv:2606. 28268v1 Announce Type: cross Abstract: Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models.