Lane2Seq: Towards Unified Lane Detection via Sequence Generation

TL;DR

Lane2Seq introduces a unified, transformer-based sequence generation framework for lane detection that simplifies the architecture and achieves state-of-the-art results across multiple benchmarks.

Contribution

It proposes a novel sequence generation approach for lane detection, unifying various formats with a simple transformer architecture and reinforcement learning-based model tuning.

Findings

Achieves 97.95% F1 on Tusimple dataset

Achieves 97.42% F1 on LLAMAS dataset

Establishes new state-of-the-art results

Abstract

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.