# Unsupervised Data Uncertainty Learning in Visual Retrieval Systems

arXiv: https://arxiv.org/abs/1902.02586 · HTML: https://mlsanity.com/paper/1902.02586/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [STUN: Self-Teaching Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.01851/) (2022)
- [Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval](https://mlsanity.com/paper/2302.01332/) (2023)
- [Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition](https://mlsanity.com/paper/2203.04446/) (2022)
- [Confidence-Calibrated Face and Kinship Verification](https://mlsanity.com/paper/2210.13905/) (2022)
- [Regressing Relative Fine-Grained Change for Sub-Groups in Unreliable Heterogeneous Data Through Deep Multi-Task Metric Learning](https://mlsanity.com/paper/2208.05800/) (2022)
- [Multimodal Indoor Localization Using Crowdsourced Radio Maps](https://mlsanity.com/paper/2311.10601/) (2023)

## Abstract (arXiv)

We introduce an unsupervised formulation to estimate heteroscedastic uncertainty in retrieval systems. We propose an extension to triplet loss that models data uncertainty for each input. Besides improving performance, our formulation models local noise in the embedding space. It quantifies input uncertainty and thus enhances interpretability of the system. This helps identify noisy observations in query and search databases. Evaluation on both image and video retrieval applications highlight the utility of our approach. We highlight our efficiency in modeling local noise using two real-world datasets: Clothing1M and Honda Driving datasets. Qualitative results illustrate our ability in identifying confusing scenarios in various domains. Uncertainty learning also enables data cleaning by detecting noisy training labels.