Localization Uncertainty Estimation for Anchor-Free Object Detection
- URL: http://arxiv.org/abs/2006.15607v6
- Date: Wed, 6 Jul 2022 05:18:04 GMT
- Title: Localization Uncertainty Estimation for Anchor-Free Object Detection
- Authors: Youngwan Lee, Joong-won Hwang, Hyung-Il Kim, Kimin Yun, Yongjin Kwon,
Yuseok Bae, Sung Ju Hwang
- Abstract summary: There are several limitations of the existing uncertainty estimation methods for anchor-based object detection.
We propose a new localization uncertainty estimation method called UAD for anchor-free object detection.
Our method captures the uncertainty in four directions of box offsets that are homogeneous, so that it can tell which direction is uncertain.
- Score: 48.931731695431374
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Since many safety-critical systems, such as surgical robots and autonomous
driving cars operate in unstable environments with sensor noise and incomplete
data, it is desirable for object detectors to take the localization uncertainty
into account. However, there are several limitations of the existing
uncertainty estimation methods for anchor-based object detection. 1) They model
the uncertainty of the heterogeneous object properties with different
characteristics and scales, such as location (center point) and scale (width,
height), which could be difficult to estimate. 2) They model box offsets as
Gaussian distributions, which is not compatible with the ground truth bounding
boxes that follow the Dirac delta distribution. 3) Since anchor-based methods
are sensitive to anchor hyper-parameters, their localization uncertainty could
also be highly sensitive to the choice of hyper-parameters. To tackle these
limitations, we propose a new localization uncertainty estimation method called
UAD for anchor-free object detection. Our method captures the uncertainty in
four directions of box offsets (left, right, top, bottom) that are homogeneous,
so that it can tell which direction is uncertain, and provide a quantitative
value of uncertainty in [0, 1]. To enable such uncertainty estimation, we
design a new uncertainty loss, negative power log-likelihood loss, to measure
the localization uncertainty by weighting the likelihood loss by its IoU, which
alleviates the model misspecification problem. Furthermore, we propose an
uncertainty-aware focal loss for reflecting the estimated uncertainty to the
classification score. Experimental results on COCO datasets demonstrate that
our method significantly improves FCOS, by up to 1.8 points, without
sacrificing computational efficiency.
Related papers
- Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection [1.8990839669542954]
We propose a cost-sensitive framework for object detection tailored to user-defined budgets.
We derive minimum thresholding requirements to prevent performance degradation.
We automate and optimize the thresholding process to maximize the failure recognition rate.
arXiv Detail & Related papers (2024-04-26T14:03:55Z) - Overcoming the Limitations of Localization Uncertainty: Efficient &
Exact Non-Linear Post-Processing and Calibration [4.199844472131921]
Existing works estimate the aleatoric uncertainty of object detectors by modeling their localization output as a Gaussian distribution.
We identify three aspects that are unaddressed in the state of the art, but warrant further exploration.
We overcome these limitations by: (1) implementing loss attenuation in EfficientDet, and proposing two deterministic methods for the exact and fast propagation of the output distribution, and (2) demonstrating on the KITTI and BDD100K datasets that the predicted uncertainty is miscalibrated.
arXiv Detail & Related papers (2023-06-15T09:20:07Z) - Safe motion planning with environment uncertainty [1.4824891788575418]
We present an approach for safe motion planning under robot state and environment uncertainties.
We first develop an approach that accounts for the landmark uncertainties during robot localization.
We then extend the state-of-the-art by computing an exact expression for the collision probability.
arXiv Detail & Related papers (2023-05-10T09:29:41Z) - 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) - Uncertainty-Aware AB3DMOT by Variational 3D Object Detection [74.8441634948334]
Uncertainty estimation is an effective tool to provide statistically accurate predictions.
In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty.
arXiv Detail & Related papers (2023-02-12T14:30:03Z) - 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) - CertainNet: Sampling-free Uncertainty Estimation for Object Detection [65.28989536741658]
Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings.
In this work, we propose a novel sampling-free uncertainty estimation method for object detection.
We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size.
arXiv Detail & Related papers (2021-10-04T17:59:31Z) - The Aleatoric Uncertainty Estimation Using a Separate Formulation with
Virtual Residuals [51.71066839337174]
Existing methods can quantify the error in the target estimation, but they tend to underestimate it.
We propose a new separable formulation for the estimation of a signal and of its uncertainty, avoiding the effect of overfitting.
We demonstrate that the proposed method outperforms a state-of-the-art technique for signal and uncertainty estimation.
arXiv Detail & Related papers (2020-11-03T12:11:27Z) - Temporal Difference Uncertainties as a Signal for Exploration [76.6341354269013]
An effective approach to exploration in reinforcement learning is to rely on an agent's uncertainty over the optimal policy.
In this paper, we highlight that value estimates are easily biased and temporally inconsistent.
We propose a novel method for estimating uncertainty over the value function that relies on inducing a distribution over temporal difference errors.
arXiv Detail & Related papers (2020-10-05T18:11:22Z)
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.