Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.18278 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911791450161152 |
|---|---|
| author | Xiong, Huiyuan Shen, Jun Zhu, Taohong Pan, Yuelong |
| author_facet | Xiong, Huiyuan Shen, Jun Zhu, Taohong Pan, Yuelong |
| contents | High-definition (HD) map is crucial for autonomous driving systems. Most existing works design map elements detection heads based on the DETR decoder. However, the initial queries lack explicit incorporation of physical positional information, and vanilla self-attention entails high computational complexity. Therefore, we propose EAN-MapNet for Efficiently constructing HD map using Anchor Neighborhoods. Firstly, we design query units based on the anchor neighborhoods, allowing non-neighborhood central anchors to effectively assist in fitting the neighborhood central anchors to the target points representing map elements. Then, we propose grouped local self-attention (GL-SA) by leveraging the relative instance relationship among the queries. This facilitates direct feature interaction among queries of the same instances, while innovatively employing local queries as intermediaries for interaction among queries from different instances. Consequently, GL-SA significantly reduces the computational complexity of self-attention while ensuring ample feature interaction among queries. On the nuScenes dataset, EAN-MapNet achieves a state-of-the-art performance with 63.0 mAP after training for 24 epochs, surpassing MapTR by 12.7 mAP. Furthermore, it considerably reduces memory consumption by 8198M compared to MapTRv2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_18278 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EAN-MapNet: Efficient Vectorized HD Map Construction with Anchor Neighborhoods Xiong, Huiyuan Shen, Jun Zhu, Taohong Pan, Yuelong Computer Vision and Pattern Recognition High-definition (HD) map is crucial for autonomous driving systems. Most existing works design map elements detection heads based on the DETR decoder. However, the initial queries lack explicit incorporation of physical positional information, and vanilla self-attention entails high computational complexity. Therefore, we propose EAN-MapNet for Efficiently constructing HD map using Anchor Neighborhoods. Firstly, we design query units based on the anchor neighborhoods, allowing non-neighborhood central anchors to effectively assist in fitting the neighborhood central anchors to the target points representing map elements. Then, we propose grouped local self-attention (GL-SA) by leveraging the relative instance relationship among the queries. This facilitates direct feature interaction among queries of the same instances, while innovatively employing local queries as intermediaries for interaction among queries from different instances. Consequently, GL-SA significantly reduces the computational complexity of self-attention while ensuring ample feature interaction among queries. On the nuScenes dataset, EAN-MapNet achieves a state-of-the-art performance with 63.0 mAP after training for 24 epochs, surpassing MapTR by 12.7 mAP. Furthermore, it considerably reduces memory consumption by 8198M compared to MapTRv2. |
| title | EAN-MapNet: Efficient Vectorized HD Map Construction with Anchor Neighborhoods |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.18278 |