Enhancing Accuracy and Robustness of Steering Angle Prediction with
Attention Mechanism
- URL: http://arxiv.org/abs/2211.11133v4
- Date: Thu, 1 Feb 2024 05:39:07 GMT
- Title: Enhancing Accuracy and Robustness of Steering Angle Prediction with
Attention Mechanism
- Authors: Swetha Nadella, Pramiti Barua, Jeremy C. Hagler, David J. Lamb, Qing
Tian
- Abstract summary: Key contribution lies in the incorporation of an attention mechanism to augment steering angle prediction accuracy and robustness.
Our findings showcase that our attention-enhanced models not only achieve state-of-the-art results in terms of steering angle Mean Squared Error (MSE) but also exhibit enhanced adversarial robustness.
- Score: 2.249916681499244
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, our focus is on enhancing steering angle prediction for
autonomous driving tasks. We initiate our exploration by investigating two
veins of widely adopted deep neural architectures, namely ResNets and
InceptionNets. Within both families, we systematically evaluate various model
sizes to understand their impact on performance. Notably, our key contribution
lies in the incorporation of an attention mechanism to augment steering angle
prediction accuracy and robustness. By introducing attention, our models gain
the ability to selectively focus on crucial regions within the input data,
leading to improved predictive outcomes. Our findings showcase that our
attention-enhanced models not only achieve state-of-the-art results in terms of
steering angle Mean Squared Error (MSE) but also exhibit enhanced adversarial
robustness, addressing critical concerns in real-world deployment. For example,
in our experiments on the Kaggle SAP and our created publicly available
datasets, attention can lead to over 6% error reduction in steering angle
prediction and boost model robustness by up to 56.09%.
Related papers
- The Risk of Federated Learning to Skew Fine-Tuning Features and
Underperform Out-of-Distribution Robustness [50.52507648690234]
Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model.
We introduce three robustness indicators and conduct experiments across diverse robust datasets.
Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
arXiv Detail & Related papers (2024-01-25T09:18:51Z) - DefectHunter: A Novel LLM-Driven Boosted-Conformer-based Code Vulnerability Detection Mechanism [3.9377491512285157]
DefectHunter is an innovative model for vulnerability identification that employs the Conformer mechanism.
This mechanism fuses self-attention with convolutional networks to capture both local, position-wise features and global, content-based interactions.
arXiv Detail & Related papers (2023-09-27T00:10:29Z) - A Unifying Framework of Attention-based Neural Load Forecasting [6.470432799969585]
We propose a unifying deep learning framework for load forecasting.
It includes time-varying feature weighting, hierarchical temporal attention, and feature-reinforced error correction.
Our framework provides an effective solution to the electric load forecasting problem.
arXiv Detail & Related papers (2023-05-08T22:46:54Z) - ARBEx: Attentive Feature Extraction with Reliability Balancing for
Robust Facial Expression Learning [1.9844265130823329]
ARBEx is a novel attentive feature extraction framework driven by Vision Transformer.
We employ learnable anchor points in the embedding space with label distributions and multi-head self-attention mechanism to optimize performance against weak predictions.
Our strategy outperforms current state-of-the-art methodologies, according to extensive experiments conducted in a variety of contexts.
arXiv Detail & Related papers (2023-05-02T15:10:01Z) - A Computer Vision Enabled damage detection model with improved YOLOv5
based on Transformer Prediction Head [0.0]
Current state-of-the-art deep learning (DL)-based damage detection models often lack superior feature extraction capability in complex and noisy environments.
DenseSPH-YOLOv5 is a real-time DL-based high-performance damage detection model where DenseNet blocks have been integrated with the backbone.
DenseSPH-YOLOv5 obtains a mean average precision (mAP) value of 85.25 %, F1-score of 81.18 %, and precision (P) value of 89.51 % outperforming current state-of-the-art models.
arXiv Detail & Related papers (2023-03-07T22:53:36Z) - Is my Driver Observation Model Overconfident? Input-guided Calibration
Networks for Reliable and Interpretable Confidence Estimates [23.449073032842076]
Driver observation models are rarely deployed under perfect conditions.
We show that raw neural network-based approaches tend to significantly overestimate their prediction quality.
We introduce Calibrated Action Recognition with Input Guidance (CARING)-a novel approach leveraging an additional neural network to learn scaling the confidences depending on the video representation.
arXiv Detail & Related papers (2022-04-10T12:43:58Z) - Human Parity on CommonsenseQA: Augmenting Self-Attention with External
Attention [66.93307963324834]
We propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear.
We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems.
The proposed system reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4% in comparison to the human accuracy of 88.9%.
arXiv Detail & Related papers (2021-12-06T18:59:02Z) - Alignment Attention by Matching Key and Query Distributions [48.93793773929006]
This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head.
It is simple to convert any models with self-attention, including pre-trained ones, to the proposed alignment attention.
On a variety of language understanding tasks, we show the effectiveness of our method in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks.
arXiv Detail & Related papers (2021-10-25T00:54:57Z) - Bayesian Attention Belief Networks [59.183311769616466]
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks.
This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights.
We show that our method outperforms deterministic attention and state-of-the-art attention in accuracy, uncertainty estimation, generalization across domains, and adversarial attacks.
arXiv Detail & Related papers (2021-06-09T17:46:22Z) - Accurate and Robust Feature Importance Estimation under Distribution
Shifts [49.58991359544005]
PRoFILE is a novel feature importance estimation method.
We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
arXiv Detail & Related papers (2020-09-30T05:29:01Z) - Self6D: Self-Supervised Monocular 6D Object Pose Estimation [114.18496727590481]
We propose the idea of monocular 6D pose estimation by means of self-supervised learning.
We leverage recent advances in neural rendering to further self-supervise the model on unannotated real RGB-D data.
arXiv Detail & Related papers (2020-04-14T13:16:36Z)
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.