StyleLess layer: Improving robustness for real-world driving

• URL: http://arxiv.org/abs/2103.13905v1
• Date: Thu, 25 Mar 2021 15:15:39 GMT
• Title: StyleLess layer: Improving robustness for real-world driving
• Authors: Julien Rebut, Andrei Bursuc, and Patrick P\'erez
• Abstract summary: Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, the full complexity of the real world cannot be encapsulated in the training data. We address this problem through a novel type of layer, dubbed StyleLess.
• Score: 5.9185565986343835
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, the full complexity of the real world cannot be encapsulated in the training data, no matter how big the dataset, and DNNs can hardly generalize to unseen conditions. Robustness to various image corruptions, caused by changing weather conditions or sensor degradation and aging, is crucial for safety when such vehicles are deployed in the real world. We address this problem through a novel type of layer, dubbed StyleLess, which enables DNNs to learn robust and informative features that can cope with varying external conditions. We propose multiple variations of this layer that can be integrated in most of the architectures and trained jointly with the main task. We validate our contribution on typical autonomous-driving tasks (detection, semantic segmentation), showing that in most cases, this approach improves predictive performance on unseen conditions (fog, rain), while preserving performance on seen conditions and objects.

Related papers

• Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models [60.87795376541144]
  A world model is a neural network capable of predicting an agent's next state given past states and actions. During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations. We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing.
  arXiv  Detail & Related papers  (2024-09-25T06:48:25Z)
• A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting [35.410769661423004]
  We present A-BDD, a large set of over 60,000 synthetically augmented images based on BDD100K. The dataset contains augmented data for rain, fog, overcast and sunglare/shadow with varying intensity levels. We provide evidence that data augmentations can play a pivotal role in closing performance gaps in adverse weather and lighting conditions.
  arXiv  Detail & Related papers  (2024-08-12T11:44:47Z)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• RainSD: Rain Style Diversification Module for Image Synthesis Enhancement using Feature-Level Style Distribution [5.500457283114346]
  This paper presents a synthetic road dataset with sensor blockage generated from real road dataset BDD100K. Using this dataset, the degradation of diverse multi-task networks for autonomous driving has been thoroughly evaluated and analyzed. The tendency of the performance degradation of deep neural network-based perception systems for autonomous vehicle has been analyzed in depth.
  arXiv  Detail & Related papers  (2023-12-31T11:30:42Z)
• Robust Monocular Depth Estimation under Challenging Conditions [81.57697198031975]
  State-of-the-art monocular depth estimation approaches are highly unreliable under challenging illumination and weather conditions. We tackle these safety-critical issues with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions.
  arXiv  Detail & Related papers  (2023-08-18T17:59:01Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey [4.731404257629232]
  Multiple perception datasets have been created for the evaluation of anomaly detection methods. This survey provides a structured and, to the best of our knowledge, complete overview and comparison of perception datasets for anomaly detection in autonomous driving.
  arXiv  Detail & Related papers  (2023-02-06T14:07:13Z)
• SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation [152.60469768559878]
  SHIFT is the largest multi-task synthetic dataset for autonomous driving. It presents discrete and continuous shifts in cloudiness, rain and fog intensity, time of day, and vehicle and pedestrian density. Our dataset and benchmark toolkit are publicly available at www.vis.xyz/shift.
  arXiv  Detail & Related papers  (2022-06-16T17:59:52Z)
• An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions [8.436505917796174]
  Deep neural networks enable impressive visual perception performance for autonomous driving. They are prone to forgetting previously learned information when adapting to different weather conditions. We propose DISC -- Domain Incremental through Statistical Correction -- a simple zero-forgetting approach which can incrementally learn new tasks.
  arXiv  Detail & Related papers  (2022-04-19T11:39:20Z)
• SoDA: Multi-Object Tracking with Soft Data Association [75.39833486073597]
  Multi-object tracking (MOT) is a prerequisite for a safe deployment of self-driving cars. We propose a novel approach to MOT that uses attention to compute track embeddings that encode dependencies between observed objects.
  arXiv  Detail & Related papers  (2020-08-18T03:40:25Z)

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.