Lane2Seq: Towards Unified Lane Detection via Sequence Generation
This addresses lane detection for autonomous driving by offering a unified approach, though it appears incremental as it builds on existing transformer architectures with reinforcement learning tuning.
The paper tackles lane detection by proposing Lane2Seq, a sequence generation framework that unifies various detection formats, achieving state-of-the-art results with 97.95% and 97.42% F1 scores on Tusimple and LLAMAS datasets.
In this paper, we present a novel sequence generation-based framework for lane detection, called Lane2Seq. It unifies various lane detection formats by casting lane detection as a sequence generation task. This is different from previous lane detection methods, which depend on well-designed task-specific head networks and corresponding loss functions. Lane2Seq only adopts a plain transformer-based encoder-decoder architecture with a simple cross-entropy loss. Additionally, we propose a new multi-format model tuning based on reinforcement learning to incorporate the task-specific knowledge into Lane2Seq. Experimental results demonstrate that such a simple sequence generation paradigm not only unifies lane detection but also achieves competitive performance on benchmarks. For example, Lane2Seq gets 97.95\% and 97.42\% F1 score on Tusimple and LLAMAS datasets, establishing a new state-of-the-art result for two benchmarks.