Structvpr: Distill Structural Knowledge With Weighting Samples For Visual Place Recognition
2022 · Yanqing Shen, Sanping Zhou, Jingwen Fu, et al.
Abstract
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely on a time-consuming re-ranking step to exploit spatial structural information for better performance. In this paper, we propose StructVPR, a novel training architecture for VPR, to enhance structural knowledge in RGB global features and thus improve feature stability in a constantly changing environment. Specifically, StructVPR uses segmentation images as a more definitive source of structural knowledge input into a CNN network and applies knowledge distillation to avoid online segmentation and inference of seg-branch in testing. Considering that not all samples contain high-quality and helpful knowledge, and some even hurt the performance of distillation, we partition samples and weigh each sample's distillation loss to enhance the expected knowledg
Authors
(none)
Tags
Stats
Related papers
- Structvpr++: Distill Structural And Semantic Knowledge With Weighting Samples For Visual Place Recognition (2025)3.58
- Structured Pruning For Efficient Visual Place Recognition (2024)2.26
- Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
- Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
- Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32
- Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
- Towards Seamless Adaptation Of Pre-trained Models For Visual Place Recognition (2024)4.84
- Mixvpr: Feature Mixing For Visual Place Recognition (2023)22.68