Although lane detection methods have shown impressive performance in
real-world scenarios, most of methods require post-processing which is not
robust enough. Therefore, end-to-end detectors like DEtection TRansformer(DETR)
have been introduced in lane detection. However, one-to-one label assignment in
DETR can degrade the training efficiency due to label semantic conflicts.
Besides, positional query in DETR is unable to provide explicit positional
prior, making it difficult to be optimized. In this paper, we present the
One-to-Several Transformer(O2SFormer). We first propose the one-to-several
label assignment, which combines one-to-one and one-to-many label assignments
to improve the training efficiency while keeping end-to-end detection. To
overcome the difficulty in optimizing one-to-one assignment. We further propose
the layer-wise soft label which adjusts the positive weight of positive lane
anchors across different decoder layers. Finally, we design the dynamic
anchor-based positional query to explore positional prior by incorporating lane
anchors into positional query. Experimental results show that O2SFormer
significantly speeds up the convergence of DETR and outperforms
Transformer-based and CNN-based detectors on the CULane dataset. Code will be
available at this https URL

本文提出了一种名为 O2SFormer 的端到端车道检测方法，通过将一对一和一对多标签分配相结合，提高训练效率，并采用层级软标签解决了 DETR 中的标签语义冲突问题，同时还提出了基于动态锚点的位置查询方法以探索位置先验，实验证明 O2SFormer 在 CULane 数据集上表现显著优于 Transformer 和 CNN 的检测器，并且代码可以从指定的链接下载。

基于单到多 Transformer 的端到端车道线检测

End to End Lane detection with One-to-Several Transformer

One-to-one label assignment in object detection has successfully obviated the
need for non-maximum suppression (NMS) as postprocessing and makes the pipeline
end-to-end. However, it triggers a new dilemma as the widely used sparse
queries cannot guarantee a high recall, while dense queries inevitably bring
more similar queries and encounter optimization difficulties. As both sparse
and dense queries are problematic, then what are the expected queries in
end-to-end object detection? This paper shows that the solution should be Dense
Distinct Queries (DDQ). Concretely, we first lay dense queries like traditional
detectors and then select distinct ones for one-to-one assignments. DDQ blends
the advantages of traditional and recent end-to-end detectors and significantly
improves the performance of various detectors including FCN, R-CNN, and DETRs.
Most impressively, DDQ-DETR achieves 52.1 AP on MS-COCO dataset within 12
epochs using a ResNet-50 backbone, outperforming all existing detectors in the
same setting. DDQ also shares the benefit of end-to-end detectors in crowded
scenes and achieves 93.8 AP on CrowdHuman. We hope DDQ can inspire researchers
to consider the complementarity between traditional methods and end-to-end
detectors. The source code can be found at
https://github.com/jshilong/DDQ.

本文介绍了一种名为 “Dense Distinct Queries” 的新型对象检测查询方法，该方法将传统检测器的密集查询和最新端到端检测器的独特查询相结合，极大地提高了在各种检测器中的性能。DDQ-DETR 在 MS-COCO 数据集上取得了 52.1 AP 的成绩，在拥挤场景中也获得了 93.8 的 AP，显示了 DDQ 的优点和可行性，可望启发研究人员考虑传统方法和端到端检测器之间的互补性。