# Stochastic Prototype Embeddings

arXiv: https://arxiv.org/abs/1909.11702 · HTML: https://mlsanity.com/paper/1909.11702/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [Probabilistic Embeddings for Cross-Modal Retrieval](https://mlsanity.com/paper/2101.05068/) (2021)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Probabilistic Representations for Video Contrastive Learning](https://mlsanity.com/paper/2204.03946/) (2022)
- [Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations](https://mlsanity.com/paper/2210.14670/) (2022)
- [Probabilistic Embeddings Revisited](https://mlsanity.com/paper/2202.06768/) (2022)
- [PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2402.18117/) (2024)
- [Uncertainties of Latent Representations in Computer Vision](https://mlsanity.com/paper/2408.14281/) (2024)
- [pEBR: A Probabilistic Approach to Embedding Based Retrieval](https://mlsanity.com/paper/2410.19349/) (2024)
- [Divergent Ensemble Networks: Enhancing Uncertainty Estimation with Shared Representations and Independent Branching](https://mlsanity.com/paper/2412.01193/) (2024)
- [Evaluating the trustworthiness of the Fr'echet Inception Distance with stochastic embedding representations](https://mlsanity.com/paper/2601.21979/) (2026)

## Abstract (arXiv)

Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far apart. We propose a probabilistic method that treats embeddings as random variables. Extending a state-of-the-art deterministic method, Prototypical Networks (Snell et al., 2017), our approach supposes the existence of a class prototype around which class instances are Gaussian distributed. The prototype posterior is a product distribution over labeled instances, and query instances are classified by marginalizing relative prototype proximity over embedding uncertainty. We describe an efficient sampler for approximate inference that allows us to train the model at roughly the same space and time cost as its deterministic sibling. Incorporating uncertainty improves performance on few-shot learning and gracefully handles label noise and out-of-distribution inputs. Compared to the state-of-the-art stochastic method, Hedged Instance Embeddings (Oh et al., 2019), we achieve superior large- and open-set classification accuracy. Our method also aligns class-discriminating features with the axes of the embedding space, yielding an interpretable, disentangled representation.