基于点云的位置识别的判别区域学习

摘要(中文译文)

基于点云的地点识别旨在通过使用由查询点云的局部特征聚合而成的全局描述符搜索数据库，从而估计粗略位置。近期先进方法利用注意力机制建立所有成对关系，以长程上下文信息增强局部特征。然而，这种操作可能将来自时变对象和任务无关区域（如汽车和地面点）的冗余且具有误导性的信息聚合到局部特征中，从而损害特征的判别能力。本文提出了一种新颖的判别性区域引导Transformer，称为DRFormer，用于基于点云的地点识别任务，通过显式构建判别性成对关系来避免聚合任务无关信息。具体而言，我们设计了一个轻量但有效的全局聚合模块，命名为LightVLAD，以高效地为定位判别性区域提供线索。基于LightVLAD，我们提出了一种判别性区域引导注意力模块，以更多地关注远距离的判别性局部特征。在该模块中，根据LightVLAD中的分配权重定位判别性区域的近似中心。中心周围的局部区域被嵌入以表征局部上下文和结构信息。接下来，在这些嵌入特征之间执行全局交互，并通过交叉注意力将全局信息分布以增强局部特征。如此，局部特征仅关注一小部分判别性区域，而不受其他无关区域的干扰。在各种基准数据集上的大量实验表明，我们的方法在基于点云的地点识别任务上优于现有最先进方法。

Abstract

Point cloud-based place recognition aims to estimate a rough location by searching the database with a global descriptor aggregated from local features of the query point cloud. Recent advanced methods exploit the attention mechanism that establishes all pairs of relationships to enhance the local features with long-range contextual information. However, this operation may aggregate redundant and misleading information from time-varying objects and task-irrelevant areas (such as cars and ground points) into the local features, thereby impairing the discriminative power of the features. In this paper, we propose a novel discriminative region-guided transformer, dubbed DRFormer, for the point cloud-based place recognition task by explicitly constructing discriminative pair relationships to avoid aggregating task-irrelevant information. Specifically, we devise a lightweight but effective global aggregation module, named LightVLAD, to efficiently provide cues for locating the discriminative regions. Based on the LightVLAD, we propose a discriminative region-guided attention module to pay more attention to distant discriminative local features. In this module, the approximate centers of discriminative regions are located according to the assignment weights in LightVLAD. The local regions around the centers are embedded to characterize the local contextual and structural information. Next, global interaction is performed between these embedded features, and the global information is distributed to enhance local features via cross-attention. As such, the local features attend to a small subset of discriminative regions without distraction from other irrelevant ones. Extensive experiments on various benchmark datasets demonstrate that our method outperforms existing state-of-the-art methods on the point cloud-based place recognition task.

如何引用

Neural networks : the official journal of the International Neural Network Society 的其他文献

• 基于锚点的快速平衡多视图聚类
• V-Sparse：从时空视觉语义压缩到文本视频检索的粗到细交互
• 一种用于多模态情感分析的文本引导跨层次融合和多任务学习框架
• 使用磁共振图像预测肿瘤病理分级的多模态混合曼巴分类模型
• RADS-PDD：面向大语言模型的、可感知可复现性的动态相似性预训练数据检测方法