SAMIRO: Spatial Attention Mutual Information Regularization with a Pre-trained Model as Oracle for Lane Detection

TL;DR

SAMIRO is a novel regularization method that uses a pre-trained model as an oracle to improve lane detection by leveraging spatial attention and mutual information, enhancing performance across multiple benchmarks.

Contribution

Introduces SAMIRO, a plug-and-play regularization technique that transfers knowledge from a pre-trained model to improve lane detection under challenging conditions.

Findings

Consistently improves lane detection accuracy across benchmarks

Effective in handling environmental challenges like occlusions and illumination

Compatible with various state-of-the-art models

Abstract

Lane detection is an important topic in the future mobility solutions. Real-world environmental challenges such as background clutter, varying illumination, and occlusions pose significant obstacles to effective lane detection, particularly when relying on data-driven approaches that require substantial effort and cost for data collection and annotation. To address these issues, lane detection methods must leverage contextual and global information from surrounding lanes and objects. In this paper, we propose a Spatial Attention Mutual Information Regularization with a pre-trained model as an Oracle, called SAMIRO. SAMIRO enhances lane detection performance by transferring knowledge from a pretrained model while preserving domain-agnostic spatial information. Leveraging SAMIRO's plug-and-play characteristic, we integrate it into various state-of-the-art lane detection approaches and conduct extensive experiments on major benchmarks such as CULane, Tusimple, and LLAMAS. The results demonstrate that SAMIRO consistently improves performance across different models and datasets. The code will be made available upon publication.