# Infinite Mixture Prototypes for Few-Shot Learning

arXiv: https://arxiv.org/abs/1902.04552 · HTML: https://mlsanity.com/paper/1902.04552/

## Key facts

- Cited by 99 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2019.

## Built on by (most cited first, 30 of 99)

- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Relational Embedding for Few-Shot Classification](https://mlsanity.com/paper/2108.09666/) (2021)
- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning](https://mlsanity.com/paper/2103.01315/) (2021)
- [HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2201.04182/) (2022)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [Novel Class Discovery without Forgetting](https://mlsanity.com/paper/2207.10659/) (2022)
- [Exemplar-Based Open-Set Panoptic Segmentation Network](https://mlsanity.com/paper/2105.08336/) (2021)
- [On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion](https://mlsanity.com/paper/2308.09942/) (2023)
- [A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs](https://mlsanity.com/paper/2110.13361/) (2021)
- [Integrative Few-Shot Learning for Classification and Segmentation](https://mlsanity.com/paper/2203.15712/) (2022)
- [Matching Feature Sets for Few-Shot Image Classification](https://mlsanity.com/paper/2204.00949/) (2022)
- [Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments](https://mlsanity.com/paper/2105.08149/) (2021)
- [Prototype Guided Federated Learning of Visual Feature Representations](https://mlsanity.com/paper/2105.08982/) (2021)
- [Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations](https://mlsanity.com/paper/2311.16681/) (2023)
- [Prototypical Reward Network for Data-Efficient RLHF](https://mlsanity.com/paper/2406.06606/) (2024)
- [Context-Aware Meta-Learning](https://mlsanity.com/paper/2310.10971/) (2023)
- [Model Predictive Task Sampling for Efficient and Robust Adaptation](https://mlsanity.com/paper/2501.11039/) (2025)
- [Learning Prototype-oriented Set Representations for Meta-Learning](https://mlsanity.com/paper/2110.09140/) (2021)
- [MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation](https://mlsanity.com/paper/2303.05105/) (2023)
- [Dense Gaussian Processes for Few-Shot Segmentation](https://mlsanity.com/paper/2110.03674/) (2021)
- [Temporal Action Segmentation with High-level Complex Activity Labels](https://mlsanity.com/paper/2108.06706/) (2021)
- [Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification](https://mlsanity.com/paper/2110.12035/) (2021)
- [Long-tail Recognition via Compositional Knowledge Transfer](https://mlsanity.com/paper/2112.06741/) (2021)
- [ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion](https://mlsanity.com/paper/2306.14770/) (2023)
- [Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning](https://mlsanity.com/paper/2101.09499/) (2021)
- [A Closer Look at Prototype Classifier for Few-shot Image Classification](https://mlsanity.com/paper/2110.05076/) (2021)
- [Hybrid Graph Neural Networks for Few-Shot Learning](https://mlsanity.com/paper/2112.06538/) (2021)

## Abstract (arXiv)

We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing prototypical methods that represent each class by a single cluster. By inferring the number of clusters, infinite mixture prototypes interpolate between nearest neighbor and prototypical representations, which improves accuracy and robustness in the few-shot regime. We show the importance of adaptive capacity for capturing complex data distributions such as alphabets, with 25% absolute accuracy improvements over prototypical networks, while still maintaining or improving accuracy on the standard Omniglot and mini-ImageNet benchmarks. In clustering labeled and unlabeled data by the same clustering rule, infinite mixture prototypes achieves state-of-the-art semi-supervised accuracy. As a further capability, we show that infinite mixture prototypes can perform purely unsupervised clustering, unlike existing prototypical methods.