Topology-Aware Uncertainty for Image Segmentation
- URL: http://arxiv.org/abs/2306.05671v3
- Date: Mon, 30 Oct 2023 05:08:33 GMT
- Title: Topology-Aware Uncertainty for Image Segmentation
- Authors: Saumya Gupta, Yikai Zhang, Xiaoling Hu, Prateek Prasanna and Chao Chen
- Abstract summary: We focus on uncertainty estimation for such tasks, so that highly uncertain, and thus error-prone structures can be identified for human annotators to verify.
We propose a joint prediction model that estimates the uncertainty of a structure while taking the neighboring structures into consideration.
We also propose a novel Probabilistic DMT to model the inherent uncertainty within each structure.
- Score: 19.248891926246383
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Segmentation of curvilinear structures such as vasculature and road networks
is challenging due to relatively weak signals and complex geometry/topology. To
facilitate and accelerate large scale annotation, one has to adopt
semi-automatic approaches such as proofreading by experts. In this work, we
focus on uncertainty estimation for such tasks, so that highly uncertain, and
thus error-prone structures can be identified for human annotators to verify.
Unlike most existing works, which provide pixel-wise uncertainty maps, we
stipulate it is crucial to estimate uncertainty in the units of topological
structures, e.g., small pieces of connections and branches. To achieve this, we
leverage tools from topological data analysis, specifically discrete Morse
theory (DMT), to first capture the structures, and then reason about their
uncertainties. To model the uncertainty, we (1) propose a joint prediction
model that estimates the uncertainty of a structure while taking the
neighboring structures into consideration (inter-structural uncertainty); (2)
propose a novel Probabilistic DMT to model the inherent uncertainty within each
structure (intra-structural uncertainty) by sampling its representations via a
perturb-and-walk scheme. On various 2D and 3D datasets, our method produces
better structure-wise uncertainty maps compared to existing works. Code
available at https://github.com/Saumya-Gupta-26/struct-uncertainty
Related papers
- Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations [80.86128012438834]
We show for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete.
We propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees.
arXiv Detail & Related papers (2024-07-10T09:13:11Z) - Learning Topological Representations for Deep Image Understanding [8.698159165261542]
We propose novel representations of topological structures in a deep learning framework.
We leverage the mathematical tools from topological data analysis to develop principled methods for better segmentation and uncertainty estimation.
arXiv Detail & Related papers (2024-03-22T17:23:37Z) - Prototype-based Aleatoric Uncertainty Quantification for Cross-modal
Retrieval [139.21955930418815]
Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space.
However, the predictions are often unreliable due to the Aleatoric uncertainty, which is induced by low-quality data, e.g., corrupt images, fast-paced videos, and non-detailed texts.
We propose a novel Prototype-based Aleatoric Uncertainty Quantification (PAU) framework to provide trustworthy predictions by quantifying the uncertainty arisen from the inherent data ambiguity.
arXiv Detail & Related papers (2023-09-29T09:41:19Z) - Shape Completion with Prediction of Uncertain Regions [4.689234879218989]
In particular, there can be an irreducible uncertainty in extended regions about the presence of entire object parts when given ambiguous object views.
We propose two novel methods for predicting such uncertain regions as straightforward extensions of any method for predicting local spatial occupancy.
We train on this dataset and test each method in shape completion and prediction of uncertain regions for known and novel object instances.
arXiv Detail & Related papers (2023-08-01T08:40:40Z) - Elongated Physiological Structure Segmentation via Spatial and Scale
Uncertainty-aware Network [28.88756808141357]
We present a spatial and scale uncertainty-aware network (SSU-Net) to highlight ambiguous regions and integrate hierarchical structure contexts.
Experiment results show that the SSU-Net performs best on cornea endothelial cell and retinal vessel segmentation tasks.
arXiv Detail & Related papers (2023-05-30T08:57:31Z) - Robust Self-Supervised LiDAR Odometry via Representative Structure
Discovery and 3D Inherent Error Modeling [67.75095378830694]
We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations.
In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases.
Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
arXiv Detail & Related papers (2022-02-27T12:52:27Z) - Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map.
We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty.
Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
arXiv Detail & Related papers (2021-01-05T18:54:11Z) - Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
Causal inferences can be obtained by standard algorithms for the updating of credal nets.
This contribution should be regarded as a systematic approach to represent structural causal models by credal networks.
Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
arXiv Detail & Related papers (2020-08-02T11:19:36Z) - Sparse representation for damage identification of structural systems [11.397437423613418]
We propose a novel two-stage sensitivity analysis-based framework for both model updating and sparse damage identification.
A sparse representation pipeline built on a quasi-$ell$ method is then presented for damage and localization quantification.
Results show that the proposed approach is capable of both localizing and quantifying structural damage with high accuracy.
arXiv Detail & Related papers (2020-06-06T18:04:35Z) - A General Framework for Consistent Structured Prediction with Implicit
Loss Embeddings [113.15416137912399]
We propose and analyze a novel theoretical and algorithmic framework for structured prediction.
We study a large class of loss functions that implicitly defines a suitable geometry on the problem.
When dealing with output spaces with infinite cardinality, a suitable implicit formulation of the estimator is shown to be crucial.
arXiv Detail & Related papers (2020-02-13T10:30:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.