Multi-level Domain Adaptation for Lane Detection

Chenguang Li, Boheng Zhang, Jia Shi, Guangliang Cheng

Abstract:

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving. Critical factors hinder the performance improvement of crossdomain lane detection that conventional methods only focus
on pixel-wise loss while ignoring shape and position priors
of lanes. To address the issue, we propose the Multi-level
Domain Adaptation (MLDA) framework, a new perspective to handle cross-domain lane detection at three complementary semantic levels of pixel, instance and category.
Specifically, at pixel level, we propose to apply cross-class
confidence constraints in self-training to tackle the imbalanced confidence distribution of lane and background. At
instance level, we go beyond pixels to treat segmented lanes
as instances and facilitate discriminative features in target domain with triplet learning, which effectively rebuilds
the semantic context of lanes and contributes to alleviating the feature confusion. At category level, we propose
an adaptive inter-domain embedding module to utilize the
position prior of lanes during adaptation. In two challenging datasets, i.e. TuSimple and CULane, our approach improves lane detection performance by a large margin with
gains of 8.8% on accuracy and 7.4% on F1-score respectively, compared with state-of-the-art domain adaptation algorithms.