Hyperbolic representation learning: Revisiting and advancing
The non-Euclidean geometry of hyperbolic spaces has recently garnered considerable
attention in the realm of representation learning. Current endeavors in hyperbolic …
attention in the realm of representation learning. Current endeavors in hyperbolic …
κhgcn: Tree-likeness modeling via continuous and discrete curvature learning
The prevalence of tree-like structures, encompassing hierarchical structures and power law
distributions, exists extensively in real-world applications, including recommendation …
distributions, exists extensively in real-world applications, including recommendation …
Learn to categorize or categorize to learn? self-coding for generalized category discovery
S Rastegar, H Doughty… - Advances in Neural …, 2024 - proceedings.neurips.cc
In the quest for unveiling novel categories at test time, we confront the inherent limitations of
traditional supervised recognition models that are restricted by a predefined category set …
traditional supervised recognition models that are restricted by a predefined category set …
Poincare resnet
M van Spengler, E Berkhout… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper introduces an end-to-end residual network that operates entirely on the Poincare
ball model of hyperbolic space. Hyperbolic learning has recently shown great potential for …
ball model of hyperbolic space. Hyperbolic learning has recently shown great potential for …
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball
S Weber, B Zöngür, N Araslanov… - Proceedings of the …, 2024 - openaccess.thecvf.com
Hierarchy is a natural representation of semantic taxonomies including the ones routinely
used in image segmentation. Indeed recent work on semantic segmentation reports …
used in image segmentation. Indeed recent work on semantic segmentation reports …
HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation
Abstract 3D shape generation from text is a fundamental task in 3D representation learning.
The text-shape pairs exhibit a hierarchical structure where a general text like" chair" covers …
The text-shape pairs exhibit a hierarchical structure where a general text like" chair" covers …
HypLL: The hyperbolic learning library
M van Spengler, P Wirth, P Mettes - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Deep learning in hyperbolic space is quickly gaining traction in the fields of machine
learning, multimedia, and computer vision. Deep networks commonly operate in Euclidean …
learning, multimedia, and computer vision. Deep networks commonly operate in Euclidean …
Leveraging Optimal Transport via Projections on Subspaces for Machine Learning Applications
C Bonet - arXiv preprint arXiv:2311.13883, 2023 - arxiv.org
Optimal Transport has received much attention in Machine Learning as it allows to compare
probability distributions by exploiting the geometry of the underlying space. However, in its …
probability distributions by exploiting the geometry of the underlying space. However, in its …
Hyperbolic Random Forests
L Doorenbos, P Márquez-Neila, R Sznitman… - arXiv preprint arXiv …, 2023 - arxiv.org
Hyperbolic space is becoming a popular choice for representing data due to the hierarchical
structure-whether implicit or explicit-of many real-world datasets. Along with it comes a need …
structure-whether implicit or explicit-of many real-world datasets. Along with it comes a need …
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather
In Federated Learning (FL), multiple clients collaboratively train a global model without
sharing private data. In semantic segmentation, the Federated source Free Domain …
sharing private data. In semantic segmentation, the Federated source Free Domain …