An Uncertainty Estimation Framework for Probabilistic Object Detection
- URL: http://arxiv.org/abs/2106.15007v1
- Date: Mon, 28 Jun 2021 22:29:59 GMT
- Title: An Uncertainty Estimation Framework for Probabilistic Object Detection
- Authors: Zongyao Lyu, Nolan B. Gutierrez, William J. Beksi
- Abstract summary: We introduce a new technique that combines two popular methods to estimate uncertainty in object detection.
Our framework employs deep ensembles and Monte Carlo dropout for approximating predictive uncertainty.
- Score: 5.83620245905973
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we introduce a new technique that combines two popular methods
to estimate uncertainty in object detection. Quantifying uncertainty is
critical in real-world robotic applications. Traditional detection models can
be ambiguous even when they provide a high-probability output. Robot actions
based on high-confidence, yet unreliable predictions, may result in serious
repercussions. Our framework employs deep ensembles and Monte Carlo dropout for
approximating predictive uncertainty, and it improves upon the uncertainty
estimation quality of the baseline method. The proposed approach is evaluated
on publicly available synthetic image datasets captured from sequences of
video.
Related papers
- One step closer to unbiased aleatoric uncertainty estimation [71.55174353766289]
We propose a new estimation method by actively de-noising the observed data.
By conducting a broad range of experiments, we demonstrate that our proposed approach provides a much closer approximation to the actual data uncertainty than the standard method.
arXiv Detail & Related papers (2023-12-16T14:59:11Z) - Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity.
The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
arXiv Detail & Related papers (2023-08-03T12:43:21Z) - Integrating Uncertainty into Neural Network-based Speech Enhancement [27.868722093985006]
Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech.
This leads to a single estimate for each input without any guarantees or measures of reliability.
We study the benefits of modeling uncertainty in clean speech estimation.
arXiv Detail & Related papers (2023-05-15T15:55:12Z) - Toward Reliable Human Pose Forecasting with Uncertainty [51.628234388046195]
We develop an open-source library for human pose forecasting, including multiple models, supporting several datasets.
We devise two types of uncertainty in the problem to increase performance and convey better trust.
arXiv Detail & Related papers (2023-04-13T17:56:08Z) - Lightweight, Uncertainty-Aware Conformalized Visual Odometry [2.429910016019183]
Data-driven visual odometry (VO) is a critical subroutine for autonomous edge robotics.
Emerging edge robotics devices like insect-scale drones and surgical robots lack a computationally efficient framework to estimate VO's predictive uncertainties.
This paper presents a novel, lightweight, and statistically robust framework that leverages conformal inference (CI) to extract VO's uncertainty bands.
arXiv Detail & Related papers (2023-03-03T20:37:55Z) - Reliability-Aware Prediction via Uncertainty Learning for Person Image
Retrieval [51.83967175585896]
UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously.
Data uncertainty captures the noise" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction.
arXiv Detail & Related papers (2022-10-24T17:53:20Z) - On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks [11.929914721626849]
We show that state-of-the-art uncertainty estimation algorithms could fail catastrophically under our proposed adversarial attack.
In particular, we aim at attacking the out-domain uncertainty estimation.
arXiv Detail & Related papers (2022-10-03T23:33:38Z) - NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural
Networks [151.03112356092575]
We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution.
We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
arXiv Detail & Related papers (2022-02-07T12:30:45Z) - Dense Uncertainty Estimation via an Ensemble-based Conditional Latent
Variable Model [68.34559610536614]
We argue that the aleatoric uncertainty is an inherent attribute of the data and can only be correctly estimated with an unbiased oracle model.
We propose a new sampling and selection strategy at train time to approximate the oracle model for aleatoric uncertainty estimation.
Our results show that our solution achieves both accurate deterministic results and reliable uncertainty estimation.
arXiv Detail & Related papers (2021-11-22T08:54:10Z) - Adversarial Attack for Uncertainty Estimation: Identifying Critical
Regions in Neural Networks [0.0]
We propose a novel method to capture data points near decision boundary in neural network that are often referred to a specific type of uncertainty.
Uncertainty estimates are derived from the input perturbations, unlike previous studies that provide perturbations on the model's parameters.
We show that the proposed method has revealed a significant outperformance over other methods and provided less risk to capture model uncertainty in machine learning.
arXiv Detail & Related papers (2021-07-15T21:30:26Z) - Labels Are Not Perfect: Improving Probabilistic Object Detection via
Label Uncertainty [12.531126969367774]
We leverage our previously proposed method for estimating uncertainty inherent in ground truth bounding box parameters.
Experimental results on the KITTI dataset show that our method surpasses both the baseline model and the models based on simple uncertaintys by up to 3.6% in terms of Average Precision.
arXiv Detail & Related papers (2020-08-10T14:49:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.