# Real-Time Fully Unsupervised Domain Adaptation for Lane Detection in Autonomous Driving

arXiv: https://arxiv.org/abs/2306.16660 · HTML: https://mlsanity.com/paper/2306.16660/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 6 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 3 of 3)

- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Ultra Fast Structure-aware Deep Lane Detection](https://mlsanity.com/paper/2004.11757/) (2020)
- [CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains](https://mlsanity.com/paper/2206.08083/) (2022)

## Built on by (most cited first, 2 of 2)

- [Autonomous Driving with Spiking Neural Networks](https://mlsanity.com/paper/2405.19687/) (2024)
- [Flashy Backdoor: Real-world Environment Backdoor Attack on SNNs with DVS Cameras](https://mlsanity.com/paper/2411.03022/) (2024)

## Abstract (arXiv)

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.