# Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems

arXiv: https://arxiv.org/abs/1901.07702 · HTML: https://mlsanity.com/paper/1901.07702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2019.

## Built on by (most cited first, 4 of 4)

- [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)
- [Risk Controlled Image Retrieval](https://mlsanity.com/paper/2307.07336/) (2023)
- [TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation](https://mlsanity.com/paper/2404.01587/) (2024)

## Abstract (arXiv)

We cast visual retrieval as a regression problem by posing triplet loss as a regression loss. This enables epistemic uncertainty estimation using dropout as a Bayesian approximation framework in retrieval. Accordingly, Monte Carlo (MC) sampling is leveraged to boost retrieval performance. Our approach is evaluated on two applications: person re-identification and autonomous car driving. Comparable state-of-the-art results are achieved on multiple datasets for the former application. We leverage the Honda driving dataset (HDD) for autonomous car driving application. It provides multiple modalities and similarity notions for ego-motion action understanding. Hence, we present a multi-modal conditional retrieval network. It disentangles embeddings into separate representations to encode different similarities. This form of joint learning eliminates the need to train multiple independent networks without any performance degradation. Quantitative evaluation highlights our approach competence, achieving 6% improvement in a highly uncertain environment.