Tightly Coupled Learning Strategy For Weakly Supervised Hierarchical Place Recognition
2022 · Y. Shen, R. Wang, W. Zuo, et al.
Abstract
Visual place recognition (VPR) is a key issue for robotics and autonomous systems. For the trade-off between time and performance, most of methods use the coarse-to-fine hierarchical architecture, which consists of retrieving top-N candidates using global features, and re-ranking top-N with local features. However, since the two types of features are usually processed independently, re-ranking may harm global retrieval, termed re-ranking confusion. Moreover, re-ranking is limited by global retrieval. In this paper, we propose a tightly coupled learning (TCL) strategy to train triplet models. Different from original triplet learning (OTL) strategy, it combines global and local descriptors for joint optimization. In addition, a bidirectional search dynamic time warping (BS-DTW) algorithm is also proposed to mine locally spatial information tailored to VPR in re-ranking. The experimental results on public benchmarks show that the models using TCL outperform the models using OTL, and TCL c
Authors
(none)
Tags
Stats
Related papers
- Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
- Mutualvpr: A Mutual Learning Framework For Resolving Supervision Inconsistencies Via Adaptive Clustering (2024)0.00
- Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics (2026)0.00
- Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
- Structured Pruning For Efficient Visual Place Recognition (2024)2.26
- Probabilistic Visual Place Recognition For Hierarchical Localization (2021)11.08
- Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
- Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32