arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.01739cs.CVcs.AI
收藏

LAM3D:利用注意力机制进行单目3D目标检测

LAM3D: Leveraging Attention for Monocular 3D Object Detection

Technical University of Cluj-Napoca(克卢日-纳波卡技术大学);Faculty of Automation and Computer Science(自动化与计算机科学学院);Vrije Universiteit Brussel(布鲁塞尔自由大学)

Diana-Alexandra Sas, Leandro Di Bella, Yangxintong Lyu, Florin Oniga, Adrian Munteanu

AI总结:

本文提出LAM3D框架,以PVTv2为骨干并利用自注意力机制进行单目3D目标检测,在KITTI基准上优于参考方法,验证了注意力机制对该任务的有效性。

摘要:

自从自注意力机制被引入以及Transformer架构被用于计算机视觉任务以来,基于视觉Transformer的架构在该领域获得了极大的普及,被用于图像分类、目标检测和图像分割等任务。然而,在视觉Transformer中高效地利用注意力机制来完成单目3D目标检测任务仍然是一个悬而未决的问题。在本文中,我们提出了LAM3D,一个利用自注意力机制进行单目3D目标检测的框架。为此,所提出的方法以Pyramid Vision Transformer v2(PVTv2)作为特征提取骨干网络和2D/3D检测机制为基础构建。我们在KITTI 3D目标检测基准上对所提出的方法进行了评估,证明了所提解决方案在自动驾驶领域的适用性,并优于参考方法。此外,由于使用了自注意力机制,LAM3D能够系统性地优于不使用自注意力的等效架构。

英文摘要:

Since the introduction of the self-attention mechanism and the adoption of the Transformer architecture for Computer Vision tasks, the Vision Transformer-based architectures gained a lot of popularity in the field, being used for tasks such as image classification, object detection and image segmentation. However, efficiently leveraging the attention mechanism in vision transformers for the Monocular 3D Object Detection task remains an open question. In this paper, we present LAM3D, a framework that Leverages self-Attention mechanism for Monocular 3D object Detection. To do so, the proposed method is built upon a Pyramid Vision Transformer v2 (PVTv2) as feature extraction backbone and 2D/3D detection machinery. We evaluate the proposed method on the KITTI 3D Object Detection Benchmark, proving the applicability of the proposed solution in the autonomous driving domain and outperforming reference methods. Moreover, due to the usage of self-attention, LAM3D is able to systematically outperform the equivalent architecture that does not employ self-attention.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑