paper-with-me

Papers

Topology-Aware Segmentation Using Discrete Morse Theory

2021-03-18 · ICLR 2021 1 · Xiaoling Hu, Yusu Wang, Li Fuxin, Dimitris Samaras, Chao Chen

In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern. Topological correctness, such as vessel connectivity and membrane closure, is crucial for downstream analysis tasks. In this paper, we propose a new approach to train deep image segmentation networks for better topological accuracy. In particular, leveraging the power of discrete Morse theory (DMT), we identify global structures, including 1D skeletons and 2D patches, which are important for topological accuracy. Trained with a novel loss based on these global structures, the network performance is significantly improved especially near topologically challenging locations (such as weak spots of connections and membranes). On diverse datasets, our method achieves superior performance on both the DICE score and topological metrics.

📄 PDF Abstract BibTeX arXiv:2103.09992

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Morse Neural Networks for Uncertainty Quantification

2023-07-02 · Benoit Dherin, Huiyi Hu, Jie Ren, Michael W. Dusenberry 외

We introduce a new deep generative model useful for uncertainty quantification: the Morse neural network, which generalizes the unnormalized Gaussian densities to have modes of high-dimensional submanifolds instead of ju…

Anomaly DetectionOne-class classifierUncertainty Quantification

Combinatorial Regularity for Relatively Perfect Discrete Morse Gradient Vector Fields of ReLU Neural Networks

2024-12-23 · Robyn Brooks, Marissa Masden

One common function class in machine learning is the class of ReLU neural networks. ReLU neural networks induce a piecewise linear decomposition of their input space called the canonical polyhedral complex. It has previo…

Learning Probabilistic Topological Representations Using Discrete Morse Theory

2022-06-03 · Xiaoling Hu, Dimitris Samaras, Chao Chen

Accurate delineation of fine-scale structures is a very important yet challenging problem. Existing methods use topological information as an additional training loss, but are ultimately making pixel-wise predictions. In…

Image SegmentationSemantic Segmentation

Monitoring Neural Training with Topology: A Footprint-Predictable Collapse Index

2026-04-28 · Alexander Kalinowski arxiv

Representational collapse, where embeddings become anisotropic and lose multi-scale structure, can erode downstream performance long before performance metrics react. We propose an online, topology-aware monitor for evol…

Morse sequences

2024-02-12 · Gilles Bertrand

We introduce the notion of a Morse sequence, which provides a simple and effective approach to discrete Morse theory. A Morse sequence is a sequence composed solely of two elementary operations, that is, expansions (the …