SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.17172 · CVPR · 2024

Lane2Seq: Towards Unified Lane Detection via Sequence Generation

Kunyang Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we present a novel sequence generationbased 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 welldesigned task-specific head networks and corresponding loss functions. Lane2Seq only adopts a plain transformerbased encoder-decoder architecture with a simple crossentropy 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 stateof-the-art result for two benchmarks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.17172")
get_code_for_paper("2402.17172")
have("2402.17172")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.17172.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.17172.svg)](https://syntology.ai/paper/2402.17172)

Connect an agent — have() is free.