# Stochastic-YOLO: Efficient Probabilistic Object Detection under Dataset Shifts

arXiv: https://arxiv.org/abs/2009.02967 · HTML: https://mlsanity.com/paper/2009.02967/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Monte Carlo DropBlock for Modelling Uncertainty in Object Detection](https://mlsanity.com/paper/2108.03614/) (2021)
- [High-Performance FPGA-based Accelerator for Bayesian Neural Networks](https://mlsanity.com/paper/2105.09163/) (2021)
- [Stochastic-Shield: A Probabilistic Approach Towards Training-Free Adversarial Defense in Quantized CNNs](https://mlsanity.com/paper/2105.06512/) (2021)
- [SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving](https://mlsanity.com/paper/2211.04009/) (2022)
- [On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications](https://mlsanity.com/paper/2111.09838/) (2021)
- [Instance-Aware Observer Network for Out-of-Distribution Object Segmentation](https://mlsanity.com/paper/2207.08782/) (2022)
- [Utilizing dataset affinity prediction in object detection to assess training data](https://mlsanity.com/paper/2311.09768/) (2023)
- [Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA](https://mlsanity.com/paper/2406.14593/) (2024)
- [Enhancing Fruit and Vegetable Detection in Unconstrained Environment with a Novel Dataset](https://mlsanity.com/paper/2409.13330/) (2024)

## Abstract (arXiv)

In image classification tasks, the evaluation of models' robustness to increased dataset shifts with a probabilistic framework is very well studied. However, object detection (OD) tasks pose other challenges for uncertainty estimation and evaluation. For example, one needs to evaluate both the quality of the label uncertainty (i.e., what?) and spatial uncertainty (i.e., where?) for a given bounding box, but that evaluation cannot be performed with more traditional average precision metrics (e.g., mAP). In this paper, we adapt the well-established YOLOv3 architecture to generate uncertainty estimations by introducing stochasticity in the form of Monte Carlo Dropout (MC-Drop), and evaluate it across different levels of dataset shift. We call this novel architecture Stochastic-YOLO, and provide an efficient implementation to effectively reduce the burden of the MC-Drop sampling mechanism at inference time. Finally, we provide some sensitivity analyses, while arguing that Stochastic-YOLO is a sound approach that improves different components of uncertainty estimations, in particular spatial uncertainties.