# Modeling Uncertainty with Hedged Instance Embedding

arXiv: https://arxiv.org/abs/1810.00319 · HTML: https://mlsanity.com/paper/1810.00319/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2018.

## Built on by (most cited first, 30 of 52)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Probabilistic Embeddings for Cross-Modal Retrieval](https://mlsanity.com/paper/2101.05068/) (2021)
- [On the Practicality of Deterministic Epistemic Uncertainty](https://mlsanity.com/paper/2107.00649/) (2021)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning](https://mlsanity.com/paper/2103.15718/) (2021)
- [Learning Fair Classifiers with Partially Annotated Group Labels](https://mlsanity.com/paper/2111.14581/) (2021)
- [Improved Probabilistic Image-Text Representations](https://mlsanity.com/paper/2305.18171/) (2023)
- [Probabilistic Representations for Video Contrastive Learning](https://mlsanity.com/paper/2204.03946/) (2022)
- [Improving Cross-Modal Retrieval with Set of Diverse Embeddings](https://mlsanity.com/paper/2211.16761/) (2022)
- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [Probabilistic Compositional Embeddings for Multimodal Image Retrieval](https://mlsanity.com/paper/2204.05845/) (2022)
- [Temperature as Uncertainty in Contrastive Learning](https://mlsanity.com/paper/2110.04403/) (2021)
- [Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation](https://mlsanity.com/paper/2106.06165/) (2021)
- [Probabilistic Prompt Learning for Dense Prediction](https://mlsanity.com/paper/2304.00779/) (2023)
- [Probabilistic Language-Image Pre-Training](https://mlsanity.com/paper/2410.18857/) (2024)
- [Out of Distribution Data Detection Using Dropout Bayesian Neural Networks](https://mlsanity.com/paper/2202.08985/) (2022)
- [STUN: Self-Teaching Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.01851/) (2022)
- [Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2503.16707/) (2025)
- [GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval](https://mlsanity.com/paper/2405.13824/) (2024)
- [SUMix: Mixup with Semantic and Uncertain Information](https://mlsanity.com/paper/2407.07805/) (2024)
- [Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides](https://mlsanity.com/paper/2208.08080/) (2022)
- [Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval](https://mlsanity.com/paper/2302.01332/) (2023)
- [ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models](https://mlsanity.com/paper/2307.00398/) (2023)
- [Just-in-Time Detection of Silent Security Patches](https://mlsanity.com/paper/2312.01241/) (2023)
- [Uncertainty-aware sign language video retrieval with probability distribution modeling](https://mlsanity.com/paper/2405.19689/) (2024)
- [Domain Generalization with Small Data](https://mlsanity.com/paper/2402.06150/) (2024)
- [Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval](https://mlsanity.com/paper/2305.07910/) (2023)
- [Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment](https://mlsanity.com/paper/2302.13251/) (2023)
- [ScaleFace: Uncertainty-aware Deep Metric Learning](https://mlsanity.com/paper/2209.01880/) (2022)

## Abstract (arXiv)

Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering. Many metric learning methods represent the input as a single point in the embedding space. Often the distance between points is used as a proxy for match confidence. However, this can fail to represent uncertainty arising when the input is ambiguous, e.g., due to occlusion or blurriness. This work addresses this issue and explicitly models the uncertainty by hedging the location of each input in the embedding space. We introduce the hedged instance embedding (HIB) in which embeddings are modeled as random variables and the model is trained under the variational information bottleneck principle. Empirical results on our new N-digit MNIST dataset show that our method leads to the desired behavior of hedging its bets across the embedding space upon encountering ambiguous inputs. This results in improved performance for image matching and classification tasks, more structure in the learned embedding space, and an ability to compute a per-exemplar uncertainty measure that is correlated with downstream performance.