# FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Network

arXiv: https://arxiv.org/abs/1905.04354 · HTML: https://mlsanity.com/paper/1905.04354/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 30 of 34)

- [CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution](https://mlsanity.com/paper/2105.05003/) (2021)
- [Rethinking Efficient Lane Detection via Curve Modeling](https://mlsanity.com/paper/2203.02431/) (2022)
- [CLRNet: Cross Layer Refinement Network for Lane Detection](https://mlsanity.com/paper/2203.10350/) (2022)
- [A Keypoint-based Global Association Network for Lane Detection](https://mlsanity.com/paper/2204.07335/) (2022)
- [Focus on Local: Detecting Lane Marker from Bottom Up via Key Point](https://mlsanity.com/paper/2105.13680/) (2021)
- [Trajeglish: Traffic Modeling as Next-Token Prediction](https://mlsanity.com/paper/2312.04535/) (2023)
- [LaneAF: Robust Multi-Lane Detection with Affinity Fields](https://mlsanity.com/paper/2103.12040/) (2021)
- [Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification](https://mlsanity.com/paper/2206.07389/) (2022)
- [Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes](https://mlsanity.com/paper/2203.15302/) (2022)
- [Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints](https://mlsanity.com/paper/2112.15351/) (2021)
- [Structure Guided Lane Detection](https://mlsanity.com/paper/2105.05403/) (2021)
- [RCLane: Relay Chain Prediction for Lane Detection](https://mlsanity.com/paper/2207.09399/) (2022)
- [ADNet: Lane Shape Prediction via Anchor Decomposition](https://mlsanity.com/paper/2308.10481/) (2023)
- [Rail Detection: An Efficient Row-based Network and A New Benchmark](https://mlsanity.com/paper/2304.05667/) (2023)
- [Lane Detection with Versatile AtrousFormer and Local Semantic Guidance](https://mlsanity.com/paper/2203.04067/) (2022)
- [Towards Driving-Oriented Metric for Lane Detection Models](https://mlsanity.com/paper/2203.16851/) (2022)
- [PriorLane: A Prior Knowledge Enhanced Lane Detection Approach Based on Transformer](https://mlsanity.com/paper/2209.06994/) (2022)
- [A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection](https://mlsanity.com/paper/2110.04079/) (2021)
- [GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting](https://mlsanity.com/paper/2201.05938/) (2022)
- [Row-wise LiDAR Lane Detection Network with Lane Correlation Refinement](https://mlsanity.com/paper/2210.08745/) (2022)
- [Monocular BEV Perception of Road Scenes via Front-to-Top View Projection](https://mlsanity.com/paper/2211.08144/) (2022)
- [Dense Hybrid Proposal Modulation for Lane Detection](https://mlsanity.com/paper/2304.14874/) (2023)
- [Decoupling the Curve Modeling and Pavement Regression for Lane Detection](https://mlsanity.com/paper/2309.10533/) (2023)
- [Monocular Lane Detection Based on Deep Learning: A Survey](https://mlsanity.com/paper/2411.16316/) (2024)
- [On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving](https://mlsanity.com/paper/2107.02488/) (2021)
- [FlowMap: Path Generation for Automated Vehicles in Open Space Using Traffic Flow](https://mlsanity.com/paper/2305.01622/) (2023)
- [Homography Guided Temporal Fusion for Road Line and Marking Segmentation](https://mlsanity.com/paper/2404.07626/) (2024)
- [Sparse Laneformer](https://mlsanity.com/paper/2404.07821/) (2024)
- [Flexible 3D Lane Detection by Hierarchical Shape MatchingFlexible 3D Lane Detection by Hierarchical Shape Matching](https://mlsanity.com/paper/2408.07163/) (2024)
- [ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation](https://mlsanity.com/paper/2108.03507/) (2021)

## Abstract (arXiv)

The search for predictive models that generalize to the long tail of sensor inputs is the central difficulty when developing data-driven models for autonomous vehicles. In this paper, we use lane detection to study modeling and training techniques that yield better performance on real world test drives. On the modeling side, we introduce a novel fully convolutional model of lane detection that learns to decode lane structures instead of delegating structure inference to post-processing. In contrast to previous works, our convolutional decoder is able to represent an arbitrary number of lanes per image, preserves the polyline representation of lanes without reducing lanes to polynomials, and draws lanes iteratively without requiring the computational and temporal complexity of recurrent neural networks. Because our model includes an estimate of the joint distribution of neighboring pixels belonging to the same lane, our formulation includes a natural and computationally cheap definition of uncertainty. On the training side, we demonstrate a simple yet effective approach to adapt the model to new environments using unsupervised style transfer. By training FastDraw to make predictions of lane structure that are invariant to low-level stylistic differences between images, we achieve strong performance at test time in weather and lighting conditions that deviate substantially from those of the annotated datasets that are publicly available. We quantitatively evaluate our approach on the CVPR 2017 Tusimple lane marking challenge, difficult CULane datasets, and a small labeled dataset of our own and achieve competitive accuracy while running at 90 FPS.