论文标题
通过基于排名的损失和大批次培训来改善基于点云的位置识别
Improving Point Cloud Based Place Recognition with Ranking-based Loss and Large Batch Training
论文作者
论文摘要
本文提出了一种简单有效的基于学习的方法，用于计算判别3D点云描述符，以实现位置识别目的。最新的最新方法具有相对复杂的体系结构，例如点变压器的多尺度卵形，结合了特征聚合模块的金字塔。我们的方法基于稀疏体素化表示，使用通道注意块增强了简单有效的3D卷积特征提取。我们在图像检索方面采用了最新进展，并根据可区分的平均精度近似提出了修改的损耗函数版本。这种损失功能需要大量培训，以获得最佳结果。通过使用多阶段反向传播来启用这一点。对流行基准的实验评估证明了我们方法的有效性，并始终如一地改善了最新技术的状态
The paper presents a simple and effective learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Recent state-of-the-art methods have relatively complex architectures such as multi-scale oyramid of point Transformers combined with a pyramid of feature aggregation modules. Our method uses a simple and efficient 3D convolutional feature extraction, based on a sparse voxelized representation, enhanced with channel attention blocks. We employ recent advances in image retrieval and propose a modified version of a loss function based on a differentiable average precision approximation. Such loss function requires training with very large batches for the best results. This is enabled by using multistaged backpropagation. Experimental evaluation on the popular benchmarks proves the effectiveness of our approach, with a consistent improvement over the state of the art
