arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.06257cs.CV
收藏

学习正确的注意点以进行特征增强

On Learning the Right Attention Point for Feature Enhancement

Shenzhen University(深圳大学);The Chinese University of Hong Kong(香港中文大学);National University of Defense Technology(国防科技大学);Simon Fraser University(西蒙弗雷泽大学)

Liqiang Lin, Pengdi Huang, Chi-Wing Fu, Kai Xu, Hao Zhang, Hui Huang

摘要:

我们提出了一种新的基于注意力的机制来学习点云处理任务的增强点特征,例如,分类和分割。与先前的工作不同,这些工作被训练来优化预先选择的一组注意点的权重,我们的方法学习定位最佳注意点,以最大限度地提高特定任务的性能,例如,点云分类重要的是,我们提倡使用单注意点来促进点特征学习中的语义理解。具体来说,我们制定了一个新的和简单的卷积,它结合了卷积特征从输入点和其相应的学习注意力点,或简称。我们的注意力机制可以很容易地集成到最先进的点云分类和分割网络中。在ModelNet40、ShapeNetPart和S3DIS等常见基准上进行的广泛实验都表明,我们启用LAP的网络始终优于各自的原始网络,以及其他竞争对手的替代方案,这些替代方案采用了多个注意点,无论是预先选择的还是在我们的学习框架下学习的。

英文摘要:

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which were trained to optimize the weights of a pre-selected set of attention points, our approach learns to locate the best attention points to maximize the performance of a specific task, e.g., point cloud classification. Importantly, we advocate the use of single attention point to facilitate semantic understanding in point feature learning. Specifically, we formulate a new and simple convolution, which combines convolutional features from an input point and its corresponding learned attention point, or LAP, for short. Our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks. Extensive experiments on common benchmarks such as ModelNet40, ShapeNetPart, and S3DIS all demonstrate that our LAP-enabled networks consistently outperform the respective original networks, as well as other competitive alternatives, which employ multiple attention points, either pre-selected or learned under our LAP framework.

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。

↑