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 2101.02672cs.CVcs.AIcs.LG
收藏

SA-Det3D:基于自注意的上下文感知三维目标检测

SA-Det3D: Self-Attention Based Context-Aware 3D Object Detection

University of Waterloo(滑铁卢大学)

Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki

摘要:

现有的基于点云的3D对象检测器使用卷积类算子来处理具有固定权重内核的局部邻域中的信息,并分层地聚合全局上下文。然而,非局部神经网络和2D视觉的自我注意力已经表明,显式地对远程交互进行建模可以产生更强大和更具竞争力的模型。在本文中,我们提出了两种变体的自注意力上下文建模在3D目标检测通过增强卷积特征与自注意力功能。我们首先将成对的自我注意力机制结合到当前最先进的BEV、体素和基于点的检测器中,并在高达1.5 3D AP的强基线模型上显示出一致的改进,同时在KITTI验证集上分别将其参数足迹和计算成本降低了15-80%和30- 50%。接下来,我们提出了一个自注意力变体,它通过在随机采样的位置上学习变形来采样最具代表性的特征的子集。这不仅使我们能够将显式全局上下文建模扩展到更大的点云,而且还导致更具鉴别力和信息量的特征描述符。我们的方法可以灵活地应用于大多数国家的最先进的检测器,提高精度和参数和计算效率。我们证明了我们提出的方法提高了KITTI,nuScenes和Waymo Open数据集上的3D目标检测性能。代码可在https://github.com/AutoVision-cloud/SA-Det3D上获得。

英文摘要:

Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and self-attention for 2D vision have shown that explicitly modeling long-range interactions can lead to more robust and competitive models. In this paper, we propose two variants of self-attention for contextual modeling in 3D object detection by augmenting convolutional features with self-attention features. We first incorporate the pairwise self-attention mechanism into the current state-of-the-art BEV, voxel and point-based detectors and show consistent improvement over strong baseline models of up to 1.5 3D AP while simultaneously reducing their parameter footprint and computational cost by 15-80% and 30-50%, respectively, on the KITTI validation set. We next propose a self-attention variant that samples a subset of the most representative features by learning deformations over randomly sampled locations. This not only allows us to scale explicit global contextual modeling to larger point-clouds, but also leads to more discriminative and informative feature descriptors. Our method can be flexibly applied to most state-of-the-art detectors with increased accuracy and parameter and compute efficiency. We show our proposed method improves 3D object detection performance on KITTI, nuScenes and Waymo Open datasets. Code is available at https://github.com/AutoVision-cloud/SA-Det3D.

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。

↑