mlsanityData to 14 Oct 2026

Hyperspherical Prototype Networks

arXiv 1901.10514 ↗First posted 29 Jan 2019cs.LG stat.MLcited by 86

Not on the map. Why?

Abstract (arXiv)

This paper introduces hyperspherical prototype networks, which unify classification and regression with prototypes on hyperspherical output spaces. For classification, a common approach is to define prototypes as the mean output vector over training examples per class. Here, we propose to use hyperspheres as output spaces, with class prototypes defined a priori with large margin separation. We position prototypes through data-independent optimization, with an extension to incorporate priors from class semantics. By doing so, we do not require any prototype updating, we can handle any training size, and the output dimensionality is no longer constrained to the number of classes. Furthermore, we generalize to regression, by optimizing outputs as an interpolation between two prototypes on the hypersphere. Since both tasks are now defined by the same loss function, they can be jointly trained for multi-task problems. Experimentally, we show the benefit of hyperspherical prototype networks for classification, regression, and their combination over other prototype methods, softmax cross-entropy, and mean squared error approaches.

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 18; 2023: 20; 2024: 13; 2025: 11; 2026: 13.

86 papers.

Sort:

By area:

  1. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  2. 2021Fully Hyperbolic Neural Networkscited by 108
  3. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 73
  4. 2024nGPT: Normalized Transformer with Representation Learning on the Hyperspherecited by 70
  5. 2021Dissecting Supervised Contrastive Learningcited by 64
  6. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  7. 2022Visual Recognition with Deep Nearest Centroidscited by 59
  8. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  9. 2021Hyperbolic Busemann Learning with Ideal Prototypescited by 41
  10. 2023Rotating Features for Object Discoverycited by 29
  11. 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
  12. 2022Maximum Class Separation as Inductive Bias in One Matrixcited by 21
38 more
  1. 2022SphereFed: Hyperspherical Federated Learningcited by 19
  2. 2024ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognitioncited by 18
  3. 2023VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distributioncited by 17
  4. 2022Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projectionscited by 16
  5. 2023Latent SDEs on Homogeneous Spacescited by 16
  6. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  7. 2023A step towards understanding why classification helps regressioncited by 15
  8. 2021Detecting Anomalies in Semantic Segmentation with Prototypescited by 13
  9. 2024HYPO: Hyperspherical Out-of-Distribution Generalizationcited by 13
  10. 2021Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptationcited by 10
  11. 2023Prototype-based Dataset Comparisoncited by 9
  12. 2025Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modelingcited by 9
  13. 2023HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learningcited by 8
  14. 2023FedFN: Feature Normalization for Alleviating Data Heterogeneity Problem in Federated Learningcited by 8
  15. 2023Equiangular Basis Vectorscited by 7
  16. 2024Temporal Test-Time Adaptation with State-Space Modelscited by 7
  17. 2025Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Spacecited by 6
  18. 2022Learning Towards the Largest Marginscited by 5
  19. 2022Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learningcited by 5
  20. 2023Improving Adversarial Robustness with Hypersphere Embedding and Angular-based Regularizationscited by 5
  21. 2023Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learningcited by 5
  22. 2024DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Modelscited by 5
  23. 2024An Overview of Prototype Formulations for Interpretable Deep Learningcited by 5
  24. 2022Prototype Based Classification from Hierarchy to Fairnesscited by 4
  25. 2022Data-Efficient Learning via Minimizing Hyperspherical Energycited by 4
  26. 2023Factorizers for Distributed Sparse Block Codescited by 4
  27. 2023ProtoDiffusion: Classifier-Free Diffusion Guidance with Prototype Learningcited by 4
  28. 2023Pairwise Similarity Learning is SimPLEcited by 4
  29. 2024Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcited by 4
  30. 2025ASIL: Augmented Structural Information Learning for Deep Graph Clustering in Hyperbolic Spacecited by 4
  31. 2021United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Taskscited by 3
  32. 2021Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detectioncited by 3
  33. 2023Robust Text Classification: Analyzing Prototype-Based Networkscited by 3
  34. 2023AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inferencecited by 3
  35. 2025Generalized Category Discovery via Token Manifold Capacity Learningcited by 3
  36. 2021Deep Repulsive Prototypes for Adversarial Robustnesscited by 2
  37. 2022Self-supervised learning with rotation-invariant kernelscited by 2
  38. 2022Beyond Learning from Next Item: Sequential Recommendation via Personalized Interest Sustainabilitycited by 2

50 most cited of 86 All 86 (JSON)