Repainting and Imitating Learning for Lane Detection

• URL: http://arxiv.org/abs/2210.05097v1
• Date: Tue, 11 Oct 2022 02:26:39 GMT
• Title: Repainting and Imitating Learning for Lane Detection
• Authors: Yue He, Minyue Jiang, Xiaoqing Ye, Liang Du, Zhikang Zou, Wei Zhang, Xiao Tan and Errui Ding
• Abstract summary: Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows. We propose a novel Repainting and Imitating Learning framework containing a pair of teacher and student. Our method introduces no extra time cost during inference and can be plug-and-play in various cutting-edge lane detection networks.
• Score: 52.5220065495956
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Current lane detection methods are struggling with the invisibility lane issue caused by heavy shadows, severe road mark degradation, and serious vehicle occlusion. As a result, discriminative lane features can be barely learned by the network despite elaborate designs due to the inherent invisibility of lanes in the wild. In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild. To achieve this, we propose a novel Repainting and Imitating Learning (RIL) framework containing a pair of teacher and student without any extra data or extra laborious labeling. Specifically, in the repainting step, an enhanced ideal virtual lane dataset is built in which only the lane regions are repainted while non-lane regions are kept unchanged, maintaining the similar distribution of lanes in the wild. The teacher model learns enhanced discriminative representation based on the virtual data and serves as the guidance for a student model to imitate. In the imitating learning step, through the scale-fusing distillation module, the student network is encouraged to generate features that mimic the teacher model both on the same scale and cross scales. Furthermore, the coupled adversarial module builds the bridge to connect not only teacher and student models but also virtual and real data, adjusting the imitating learning process dynamically. Note that our method introduces no extra time cost during inference and can be plug-and-play in various cutting-edge lane detection networks. Experimental results prove the effectiveness of the RIL framework both on CULane and TuSimple for four modern lane detection methods. The code and model will be available soon.

Related papers

• Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning [63.850451635362425]
  Continual learning requires a model to adapt to ongoing changes in the data distribution. We show that the combination of a large language model and an image generation model can similarly provide useful premonitions. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem.
  arXiv  Detail & Related papers  (2024-03-12T06:29:54Z)
• Decoupling the Curve Modeling and Pavement Regression for Lane Detection [67.22629246312283]
  curve-based lane representation is a popular approach in many lane detection methods. We propose a new approach to the lane detection task by decomposing it into two parts: curve modeling and ground height regression.
  arXiv  Detail & Related papers  (2023-09-19T11:24:14Z)
• Contrastive Learning for Lane Detection via cross-similarity [0.5249805590164902]
  Lane markings in road scenes pose a challenge due to their intricate nature, which is susceptible to unfavorable conditions. We present Contrastive Learning for Lane Detection via cross-similarity (CLLD) to enhance the resilience of lane detection models in real-world scenarios.
  arXiv  Detail & Related papers  (2023-08-16T09:16:05Z)
• DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving [64.57963116462757]
  State-of-the-art methods usually follow the Teacher-Student' paradigm. Student model only has access to raw sensor data and conducts behavior cloning on the data collected by the teacher model. We propose DriveAdapter, which employs adapters with the feature alignment objective function between the student (perception) and teacher (planning) modules.
  arXiv  Detail & Related papers  (2023-08-01T09:21:53Z)
• LVLane: Deep Learning for Lane Detection and Classification in Challenging Conditions [2.5641096293146712]
  We present an end-to-end lane detection and classification system based on deep learning methodologies. In our study, we introduce a unique dataset meticulously curated to encompass scenarios that pose significant challenges for state-of-the-art (SOTA) lane localization models. We propose a CNN-based classification branch, seamlessly integrated with the detector, facilitating the identification of distinct lane types.
  arXiv  Detail & Related papers  (2023-07-13T16:09:53Z)
• Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision [10.819463015526832]
  This paper presents the first self-supervised learning method to train a model to infer a spatially grounded lane-level road network graph. A formal road lane network model is presented and proves that any structured road scene can be represented by a directed acyclic graph of at most depth three. Results show that the model can generalize to new road layouts, unlike previous approaches, demonstrating its potential for real-world application.
  arXiv  Detail & Related papers  (2021-07-05T04:34:51Z)
• Self-Damaging Contrastive Learning [92.34124578823977]
  Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution. This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes. Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
  arXiv  Detail & Related papers  (2021-06-06T00:04:49Z)
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units [11.968518335236787]
  Lane detection will remain an open problem for some time to come. A-temporal network with double Conal Gated Recurrent Units (ConvGRUs) proposed to address lane detection in challenging scenes. Our model can outperform the state-of-the-art lane detection models.
  arXiv  Detail & Related papers  (2020-08-10T06:50:48Z)
• Learning Invariant Representations for Reinforcement Learning without Reconstruction [98.33235415273562]
  We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Bisimulation metrics quantify behavioral similarity between states in continuous MDPs. We demonstrate the effectiveness of our method at disregarding task-irrelevant information using modified visual MuJoCo tasks.
  arXiv  Detail & Related papers  (2020-06-18T17:59:35Z)

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.