Improving Uncertainty of Deep Learning-based Object Classification on
Radar Spectra using Label Smoothing
- URL: http://arxiv.org/abs/2109.12851v1
- Date: Mon, 27 Sep 2021 07:49:38 GMT
- Title: Improving Uncertainty of Deep Learning-based Object Classification on
Radar Spectra using Label Smoothing
- Authors: Kanil Patel, William Beluch, Kilian Rambach, Michael Pfeiffer, Bin
Yang
- Abstract summary: We learn deep radar spectra classifiers which offer robust real-time uncertainty estimates using label smoothing during training.
In this article, we exploit radar-specific know-how to define soft labels which encourage the classifiers to learn to output high-quality uncertainty estimates.
Our investigations show how simple radar knowledge can easily be combined with complex data-driven learning algorithms to yield safe automotive radar perception.
- Score: 9.438141018800636
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Object type classification for automotive radar has greatly improved with
recent deep learning (DL) solutions, however these developments have mostly
focused on the classification accuracy. Before employing DL solutions in
safety-critical applications, such as automated driving, an indispensable
prerequisite is the accurate quantification of the classifiers' reliability.
Unfortunately, DL classifiers are characterized as black-box systems which
output severely over-confident predictions, leading downstream decision-making
systems to false conclusions with possibly catastrophic consequences. We find
that deep radar classifiers maintain high-confidences for ambiguous, difficult
samples, e.g. small objects measured at large distances, under domain shift and
signal corruptions, regardless of the correctness of the predictions. The focus
of this article is to learn deep radar spectra classifiers which offer robust
real-time uncertainty estimates using label smoothing during training. Label
smoothing is a technique of refining, or softening, the hard labels typically
available in classification datasets. In this article, we exploit
radar-specific know-how to define soft labels which encourage the classifiers
to learn to output high-quality calibrated uncertainty estimates, thereby
partially resolving the problem of over-confidence. Our investigations show how
simple radar knowledge can easily be combined with complex data-driven learning
algorithms to yield safe automotive radar perception.
Related papers
- Credible Teacher for Semi-Supervised Object Detection in Open Scene [106.25850299007674]
In Open Scene Semi-Supervised Object Detection (O-SSOD), unlabeled data may contain unknown objects not observed in the labeled data.
It is detrimental to the current methods that mainly rely on self-training, as more uncertainty leads to the lower localization and classification precision of pseudo labels.
We propose Credible Teacher, an end-to-end framework to prevent uncertain pseudo labels from misleading the model.
arXiv Detail & Related papers (2024-01-01T08:19:21Z) - XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification.
XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations.
Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
arXiv Detail & Related papers (2023-10-09T08:07:04Z) - Unsupervised Domain Adaptation for Self-Driving from Past Traversal
Features [69.47588461101925]
We propose a method to adapt 3D object detectors to new driving environments.
Our approach enhances LiDAR-based detection models using spatial quantized historical features.
Experiments on real-world datasets demonstrate significant improvements.
arXiv Detail & Related papers (2023-09-21T15:00:31Z) - GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects.
We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables.
The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
arXiv Detail & Related papers (2022-07-06T06:26:17Z) - Contrastive Learning for Automotive mmWave Radar Detection Points Based
Instance Segmentation [9.491866334097114]
We propose a contrastive learning approach for implementing radar detection points-based instance segmentation.
We define the positive and negative samples according to the ground-truth label, apply the contrastive loss to train the model first, and then perform training for the following downstream task.
Experiments show that when the ground-truth information is only available for 5% of the training data, our method still achieves a comparable performance to the approach trained in a supervised manner with 100% ground-truth information.
arXiv Detail & Related papers (2022-03-13T03:00:34Z) - Unsupervised Domain Adaptation across FMCW Radar Configurations Using
Margin Disparity Discrepancy [17.464353263281907]
In this work, we consider the problem of unsupervised domain adaptation across radar configurations in the context of deep-learning human activity classification.
We focus on the theory-inspired technique of Margin Disparity Discrepancy, which has already been proved successful in the area of computer vision.
Our experiments extend this technique to radar data, achieving a comparable accuracy to fewshot supervised approaches for the same classification problem.
arXiv Detail & Related papers (2022-03-09T09:11:06Z) - DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections
for Object Classification [0.5669790037378094]
We propose a method that combines classical radar signal processing and Deep Learning algorithms.
The proposed method can be used for example to improve automatic emergency braking or collision avoidance systems.
arXiv Detail & Related papers (2022-02-17T08:45:11Z) - Unsupervised Learning Architecture for Classifying the Transient Noise
of Interferometric Gravitational-wave Detectors [2.8555963243398073]
transient noise with non-stationary and non-Gaussian features occurs at a high rate.
Classification of transient noise can offer clues for exploring its origin and improving the performance of the detector.
In this study, we propose an unsupervised learning architecture for the classification of transient noise.
arXiv Detail & Related papers (2021-11-19T05:37:06Z) - Towards Reducing Labeling Cost in Deep Object Detection [61.010693873330446]
We propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector.
Our method is able to pseudo-label the very confident predictions, suppressing a potential distribution drift.
arXiv Detail & Related papers (2021-06-22T16:53:09Z) - Investigation of Uncertainty of Deep Learning-based Object
Classification on Radar Spectra [8.797293761152604]
Deep learning (DL) has attracted increasing interest to improve object type classification for automotive radar.
Current DL research has investigated how uncertainties of predictions can be quantified.
In this article, we evaluate the potential of these methods for safe, automotive radar perception.
arXiv Detail & Related papers (2021-06-01T09:50:19Z) - Deep Learning and Traffic Classification: Lessons learned from a
commercial-grade dataset with hundreds of encrypted and zero-day applications [72.02908263225919]
We share our experience on a commercial-grade DL traffic classification engine.
We identify known applications from encrypted traffic, as well as unknown zero-day applications.
We propose a novel technique, tailored for DL models, that is significantly more accurate and light-weight than the state of the art.
arXiv Detail & Related papers (2021-04-07T15:21:22Z)
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.