Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors

• URL: http://arxiv.org/abs/2506.10146v1
• Date: Wed, 11 Jun 2025 19:51:06 GMT
• Title: Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors
• Authors: Tejaswi Kasarla, Max van Spengler, Pascal Mettes,
• Abstract summary: A hierarchical hyperbolic embedding is preferred for discriminating in- and out-of-distribution samples.<n>We outline a hyperbolic class embedding algorithm that jointly optimize for hierarchical distortion and balancing between shallow and wide subhierarchies.<n>We show that our hyperbolic embeddings outperform other hyperbolic approaches, beat state-of-the-art contrastive methods, and enable hierarchical out-of-distribution generalization.
• Score: 13.816378672996784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Out-of-distribution recognition forms an important and well-studied problem in deep learning, with the goal to filter out samples that do not belong to the distribution on which a network has been trained. The conclusion of this paper is simple: a good hierarchical hyperbolic embedding is preferred for discriminating in- and out-of-distribution samples. We introduce Balanced Hyperbolic Learning. We outline a hyperbolic class embedding algorithm that jointly optimizes for hierarchical distortion and balancing between shallow and wide subhierarchies. We then use the class embeddings as hyperbolic prototypes for classification on in-distribution data. We outline how to generalize existing out-of-distribution scoring functions to operate with hyperbolic prototypes. Empirical evaluations across 13 datasets and 13 scoring functions show that our hyperbolic embeddings outperform existing out-of-distribution approaches when trained on the same data with the same backbones. We also show that our hyperbolic embeddings outperform other hyperbolic approaches, beat state-of-the-art contrastive methods, and natively enable hierarchical out-of-distribution generalization.

Related papers

• Long-Tailed Learning for Generalized Category Discovery [0.0]
  We propose a novel framework that performs generalized category discovery in long-tailed distributions.<n>We first present a self-guided labeling technique that uses a learnable distribution to generate pseudo-labels.<n>We then introduce a representation balancing process to derive discriminative representations.
  arXiv  Detail & Related papers  (2025-06-08T02:01:49Z)
• Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin [49.12496652756007]
  We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius. In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric.
  arXiv  Detail & Related papers  (2023-09-18T14:51:46Z)
• Hyperbolic Random Forests [15.992363138277442]
  We generalize the well-known random forests to hyperbolic space. We do this by redefining the notion of a split using horospheres. We also outline a new method for combining classes based on their lowest common ancestor and a class-balanced version of the large-margin loss.
  arXiv  Detail & Related papers  (2023-08-25T10:01:53Z)
• HMSN: Hyperbolic Self-Supervised Learning by Clustering with Ideal Prototypes [7.665392786787577]
  We use hyperbolic representation space for self-supervised representation learning for prototype-based clustering approaches. We extend the Masked Siamese Networks to operate on the Poincar'e ball model of hyperbolic space. Unlike previous methods we project to the hyperbolic space at the output of the encoder network and utilise a hyperbolic projection head to ensure that the representations used for downstream tasks remain hyperbolic.
  arXiv  Detail & Related papers  (2023-05-18T12:38:40Z)
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization [52.369435664689995]
  We introduce a textitHyperbolic Regularization powered Collaborative Filtering (HRCF) and design a geometric-aware hyperbolic regularizer. Specifically, the proposal boosts optimization procedure via the root alignment and origin-aware penalty. Our proposal is able to tackle the over-smoothing problem caused by hyperbolic aggregation and also brings the models a better discriminative ability.
  arXiv  Detail & Related papers  (2022-04-18T06:11:44Z)
• Hyperbolic Vision Transformers: Combining Improvements in Metric Learning [116.13290702262248]
  We propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. We evaluate the proposed model with six different formulations on four datasets.
  arXiv  Detail & Related papers  (2022-03-21T09:48:23Z)
• Relieving Long-tailed Instance Segmentation via Pairwise Class Balance [85.53585498649252]
  Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. We propose a novel Pairwise Class Balance (PCB) method, built upon a confusion matrix which is updated during training to accumulate the ongoing prediction preferences.
  arXiv  Detail & Related papers  (2022-01-08T07:48:36Z)
• A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification [7.8176853587105075]
  Hyperbolic spaces offer a mathematically appealing approach for learning hierarchical representations of symbolic data. This work proposes a fully hyperbolic model for multi-class multi-label classification, which performs all operations in hyperbolic space. A thorough analysis sheds light on the impact of each component in the final prediction and showcases its ease of integration with Euclidean layers.
  arXiv  Detail & Related papers  (2020-10-05T14:42:56Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)
• Embedding Propagation: Smoother Manifold for Few-Shot Classification [131.81692677836202]
  We propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification. We empirically show that embedding propagation yields a smoother embedding manifold. We show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16% points.
  arXiv  Detail & Related papers  (2020-03-09T13:51:09Z)

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.