Localized Persistent Homologies for more Effective Deep Learning
Persistent Homologies have been successfully used to increase the performance of deep networks trained to detect curvilinear structures and to improve the topological quality of the results. However, existing methods are very global and ignore the location of topological features. In this paper, we introduce an approach that relies on a new filtration function to account for location during network training. We demonstrate experimentally on 2D images of roads and 3D image stacks of neural processes that networks trained in this manner are better at recovering the topology of the curvilinear structures they extract.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
Weighted persistent homology for osmolyte molecular aggregation and hydrogen-bonding network analysis
It has long been observed that trimethylamin N-oxide (TMAO) and urea demonstrate dramatically different properties in a protein folding process. Even with the enormous theoretical and experimental research work of the tw…
Protein FoldingTraceCAD: Trace-Guided Repair for Agentic CAD Generation
LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that l…
Topological data analysis of human vowels: Persistent homologies across representation spaces
Topological Data Analysis (TDA) has been successfully used for various tasks in signal/image processing, from visualization to supervised/unsupervised classification. Often, topological characteristics are obtained from …
Gender PredictionTopological Data AnalysisCollective Intelligence and Neurodynamics: Functional Homologies
A deep understanding of the dynamics of the human nervous system requires the simultaneous study of multiple spatiotemporal scales from the level of neurotransmitters up to the level of human cultures. This is likely imp…
Multi-dimensional Persistent Sheaf Laplacians for Image Analysis
We propose a multi-dimensional persistent sheaf Laplacian (MPSL) framework on simplicial complexes for image analysis. The proposed method is motivated by the strong sensitivity of commonly used dimensionality reduction …
Dimensionality Reduction