paper-with-me

홈 › Papers

Stereographic Spherical Sliced Wasserstein Distances

2024-02-04 · Huy Tran, Yikun Bai, Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Rocio Diaz Martin, Soheil Kolouri

Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning. The utility of optimal transport-based distances, such as the Wasserstein distance, for comparing probability measures has spurred active research in developing computationally efficient variations of these distances for spherical probability measures. This paper introduces a high-speed and highly parallelizable distance for comparing spherical measures using the stereographic projection and the generalized Radon transform, which we refer to as the Stereographic Spherical Sliced Wasserstein (S3W) distance. We carefully address the distance distortion caused by the stereographic projection and provide an extensive theoretical analysis of our proposed metric and its rotationally invariant variation. Finally, we evaluate the performance of the proposed metrics and compare them with recent baselines in terms of both speed and accuracy through a wide range of numerical studies, including gradient flows and self-supervised learning. Our code is available at https://github.com/mint-vu/s3wd.

📄 PDF Abstract BibTeX arXiv:2402.02345

Code (1)

mint-vu/s3wd 공식 구현 pytorch

Tasks

Representation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data

2024-11-09 · Xinran Liu, Yikun Bai, Rocío Díaz Martín, Kaiwen Shi 외

Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such as spherical and stereographic spherica…

3D Point Cloud InterpolationComputational Efficiency

Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projections

2022-11-18 · Clément Bonet, Laetitia Chapel, Lucas Drumetz, Nicolas Courty

It has been shown beneficial for many types of data which present an underlying hierarchical structure to be embedded in hyperbolic spaces. Consequently, many tools of machine learning were extended to such spaces, but o…

image-classificationImage Classification

Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates

2024-02-02 · Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers 외

The Sliced-Wasserstein (SW) distance between probability measures is defined as the average of the Wasserstein distances resulting for the associated one-dimensional projections. As a consequence, the SW distance can be …

Spherical Sliced-Wasserstein

2022-06-17 · Clément Bonet, Paul Berg, Nicolas Courty, François Septier 외

Many variants of the Wasserstein distance have been introduced to reduce its original computational burden. In particular the Sliced-Wasserstein distance (SW), which leverages one-dimensional projections for which a clos…

Density EstimationVariational Inference

S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling

2025-07-16 · Suman Adhya, Debarshi Kumar Sanyal arxiv

Modeling latent representations in a hyperspherical space has proven effective for capturing directional similarities in high-dimensional text data, benefiting topic modeling. Variational autoencoder-based neural topic m…

Topic Models