Benchmarking Probabilistic Deep Learning Methods for License Plate
Recognition
- URL: http://arxiv.org/abs/2302.01427v1
- Date: Thu, 2 Feb 2023 21:37:42 GMT
- Title: Benchmarking Probabilistic Deep Learning Methods for License Plate
Recognition
- Authors: Franziska Schirrmacher, Benedikt Lorch, Anatol Maier, Christian Riess
- Abstract summary: We propose to model the prediction uncertainty for license plate recognition explicitly.
Experiments on synthetic noisy or blurred low-resolution images show that the predictive uncertainty reliably finds wrong predictions.
- Score: 11.772116128679116
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning-based algorithms for automated license plate recognition implicitly
assume that the training and test data are well aligned. However, this may not
be the case under extreme environmental conditions, or in forensic applications
where the system cannot be trained for a specific acquisition device.
Predictions on such out-of-distribution images have an increased chance of
failing. But this failure case is oftentimes hard to recognize for a human
operator or an automated system. Hence, in this work we propose to model the
prediction uncertainty for license plate recognition explicitly. Such an
uncertainty measure allows to detect false predictions, indicating an analyst
when not to trust the result of the automated license plate recognition. In
this paper, we compare three methods for uncertainty quantification on two
architectures. The experiments on synthetic noisy or blurred low-resolution
images show that the predictive uncertainty reliably finds wrong predictions.
We also show that a multi-task combination of classification and
super-resolution improves the recognition performance by 109\% and the
detection of wrong predictions by 29 %.
Related papers
- Error-Driven Uncertainty Aware Training [7.702016079410588]
Error-Driven Uncertainty Aware Training aims to enhance the ability of neural models to estimate their uncertainty correctly.
The EUAT approach operates during the model's training phase by selectively employing two loss functions depending on whether the training examples are correctly or incorrectly predicted.
We evaluate EUAT using diverse neural models and datasets in the image recognition domains considering both non-adversarial and adversarial settings.
arXiv Detail & Related papers (2024-05-02T11:48:14Z) - 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) - Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
In safety-critical applications of machine learning, it is often desirable for a model to be conservative.
We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
arXiv Detail & Related papers (2023-06-08T07:05:36Z) - A Data-Driven Measure of Relative Uncertainty for Misclassification
Detection [25.947610541430013]
We introduce a data-driven measure of uncertainty relative to an observer for misclassification detection.
By learning patterns in the distribution of soft-predictions, our uncertainty measure can identify misclassified samples.
We demonstrate empirical improvements over multiple image classification tasks, outperforming state-of-the-art misclassification detection methods.
arXiv Detail & Related papers (2023-06-02T17:32:03Z) - 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) - STUN: Self-Teaching Uncertainty Estimation for Place Recognition [10.553297191854837]
This paper proposes STUN, a self-teaching framework that learns to simultaneously predict the place and estimate the prediction uncertainty given an input image.
Our experimental results on the large-scale Pittsburgh30k dataset demonstrate that STUN outperforms the state-of-the-art methods in both recognition accuracy and the quality of uncertainty estimation.
arXiv Detail & Related papers (2022-03-03T16:59:42Z) - 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) - Can We Leverage Predictive Uncertainty to Detect Dataset Shift and
Adversarial Examples in Android Malware Detection? [20.96638126913256]
We re-design and build 24 Android malware detectors by transforming four off-the-shelf detectors with six calibration methods.
We quantify their uncertainties with nine metrics, including three metrics dealing with data imbalance.
It is an open problem to quantify the uncertainty associated with the predicted labels of adversarial examples.
arXiv Detail & Related papers (2021-09-20T16:16:25Z) - An Uncertainty Estimation Framework for Probabilistic Object Detection [5.83620245905973]
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.
arXiv Detail & Related papers (2021-06-28T22:29:59Z) - Learning Uncertainty For Safety-Oriented Semantic Segmentation In
Autonomous Driving [77.39239190539871]
We show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving.
We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function.
We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods.
arXiv Detail & Related papers (2021-05-28T09:23:05Z) - The Hidden Uncertainty in a Neural Networks Activations [105.4223982696279]
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data.
This work investigates whether this distribution correlates with a model's epistemic uncertainty, thus indicating its ability to generalise to novel inputs.
arXiv Detail & Related papers (2020-12-05T17:30:35Z)
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.