Real-Time Fully Unsupervised Domain Adaptation for Lane Detection in Autonomous Driving
While deep neural networks are being utilized heavily for autonomous driving, they need to be adapted to new unseen environmental conditions for which they were not trained. We focus on a safety critical application of lane detection, and propose a lightweight, fully unsupervised, real-time adaptation approach that only adapts the batch-normalization parameters of the model. We demonstrate that our technique can perform inference, followed by on-device adaptation, under a tight constraint of 30 FPS on Nvidia Jetson Orin. It shows similar accuracy (avg. of 92.19%) as a state-of-the-art semi-supervised adaptation algorithm but which does not support real-time adaptation.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingAvgDomain AdaptationLane DetectionUnsupervised Domain AdaptationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization
Temporal Action Localization (TAL) is a complex task that poses relevant challenges, particularly when attempting to generalize on new -- unseen -- domains in real-world applications. These scenarios, despite realistic, …
Action DetectionAction LocalizationDomain AdaptationTemporal Action Localization+1Restyling Data: Application to Unsupervised Domain Adaptation
Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth acquisition, which in some cases is ver…
Domain AdaptationStyle TransferSynthetic Data GenerationUnsupervised Domain AdaptationFew-shot time-series anomaly detection with unsupervised domain adaptation
Anomaly detection for time-series data is crucial in the management of systems for streaming applications, computational services, and cloud platforms. The majority of current few-shot learning (FSL) approaches are suppo…
Anomaly DetectionDomain AdaptationFew-Shot LearningTime Series+4A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation
We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convo…
Domain AdaptationScene SegmentationCARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains
Unsupervised Domain Adaptation demonstrates great potential to mitigate domain shifts by transferring models from labeled source domains to unlabeled target domains. While Unsupervised Domain Adaptation has been applied …
2D Semantic SegmentationAutonomous DrivingDomain AdaptationLane Detection+4