# Learning Lightweight Lane Detection CNNs by Self Attention Distillation

arXiv: https://arxiv.org/abs/1908.00821 · HTML: https://mlsanity.com/paper/1908.00821/

## Key facts

- Cited by 162 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 2 Aug 2019.

## Built on by (most cited first, 30 of 162)

- [PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark](https://mlsanity.com/paper/2203.11089/) (2022)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images](https://mlsanity.com/paper/2110.01997/) (2021)
- [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)
- [YOLOP: You Only Look Once for Panoptic Driving Perception](https://mlsanity.com/paper/2108.11250/) (2021)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)
- [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)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2109.12484/) (2021)
- [Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection](https://mlsanity.com/paper/2301.02371/) (2023)
- [Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation](https://mlsanity.com/paper/2103.08273/) (2021)
- [ONCE-3DLanes: Building Monocular 3D Lane Detection](https://mlsanity.com/paper/2205.00301/) (2022)
- [Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model](https://mlsanity.com/paper/2210.04017/) (2022)
- [LaneAF: Robust Multi-Lane Detection with Affinity Fields](https://mlsanity.com/paper/2103.12040/) (2021)
- [CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention](https://mlsanity.com/paper/2209.07989/) (2022)
- [Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification](https://mlsanity.com/paper/2206.07389/) (2022)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations](https://mlsanity.com/paper/2310.20494/) (2023)
- [PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model](https://mlsanity.com/paper/2204.02681/) (2022)
- [Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes](https://mlsanity.com/paper/2203.15302/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints](https://mlsanity.com/paper/2112.15351/) (2021)
- [HybridNets: End-to-End Perception Network](https://mlsanity.com/paper/2203.09035/) (2022)
- [MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition](https://mlsanity.com/paper/2208.05768/) (2022)
- [Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving](https://mlsanity.com/paper/2203.00858/) (2022)
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022)
- [Towards Knowledge-driven Autonomous Driving](https://mlsanity.com/paper/2312.04316/) (2023)
- [Structure Guided Lane Detection](https://mlsanity.com/paper/2105.05403/) (2021)

## Abstract (arXiv)

Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context, these models often fail in challenging scenarios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps extracted from a model trained to a reasonable level would encode rich contextual information. The valuable contextual information can be used as a form of 'free' supervision for further representation learning through performing topdown and layer-wise attention distillation within the network itself. SAD can be easily incorporated in any feedforward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three popular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet-18 and ResNet-34. The lightest model, ENet-SAD, performs comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 x fewer parameters and runs 10 x faster compared to the state-of-the-art SCNN, while still achieving compelling performance in all benchmarks. Our code is available at https://github.com/cardwing/Codes-for-Lane-Detection.