A Simple Hierarchical Pooling Data Structure for Loop Closure

2015/11/20 by Xiaohan Fei, Fei, Xiaohan, Konstantine Tsotsos +3
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics (cs.RO) #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.1511.06489

openalex publication_date 2015/11/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a data structure obtained by hierarchically averaging bag-of-word descriptors during a sequence of views that achieves average speedups in large-scale loop closure applications ranging from 4 to 20 times on benchmark datasets. Although simple, the method works as well as sophisticated agglomerative schemes at a fraction of the cost with minimal loss of performance.

Citations

• The information bottleneck method
• A Probabilistic Theory of Deep Learning
• Vision meets robotics: The KITTI dataset
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Related

• LoopNet: A Multitasking Few-Shot Learning Approach for Loop Closure in Large Scale SLAM
• Bundled References: An Abstraction for Highly-Concurrent Linearizable Range Queries
• SLC²-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM
• Accelerating the Global Aggregation of Local Explanations
• LOOPRAG: Enhancing Loop Transformation Optimization with Retrieval-Augmented Large Language Models