Ranking-aware Continual Learning for LiDAR Place Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xufei, Tian, Gengxuan, Zhao, Junqiao, Tao, Siyue, Gu, Qiwen, Yu, Qiankun, Feng, Tiantian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915283278495744
author Wang, Xufei
Tian, Gengxuan
Zhao, Junqiao
Tao, Siyue
Gu, Qiwen
Yu, Qiankun
Feng, Tiantian
author_facet Wang, Xufei
Tian, Gengxuan
Zhao, Junqiao
Tao, Siyue
Gu, Qiwen
Yu, Qiankun
Feng, Tiantian
contents Place recognition plays a significant role in SLAM, robot navigation, and autonomous driving applications. Benefiting from deep learning, the performance of LiDAR place recognition (LPR) has been greatly improved. However, many existing learning-based LPR methods suffer from catastrophic forgetting, which severely harms the performance of LPR on previously trained places after training on a new environment. In this paper, we introduce a continual learning framework for LPR via Knowledge Distillation and Fusion (KDF) to alleviate forgetting. Inspired by the ranking process of place recognition retrieval, we present a ranking-aware knowledge distillation loss that encourages the network to preserve the high-level place recognition knowledge. We also introduce a knowledge fusion module to integrate the knowledge of old and new models for LiDAR place recognition. Our extensive experiments demonstrate that KDF can be applied to different networks to overcome catastrophic forgetting, surpassing the state-of-the-art methods in terms of mean Recall@1 and forgetting score.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07198
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ranking-aware Continual Learning for LiDAR Place Recognition
Wang, Xufei
Tian, Gengxuan
Zhao, Junqiao
Tao, Siyue
Gu, Qiwen
Yu, Qiankun
Feng, Tiantian
Computer Vision and Pattern Recognition
Place recognition plays a significant role in SLAM, robot navigation, and autonomous driving applications. Benefiting from deep learning, the performance of LiDAR place recognition (LPR) has been greatly improved. However, many existing learning-based LPR methods suffer from catastrophic forgetting, which severely harms the performance of LPR on previously trained places after training on a new environment. In this paper, we introduce a continual learning framework for LPR via Knowledge Distillation and Fusion (KDF) to alleviate forgetting. Inspired by the ranking process of place recognition retrieval, we present a ranking-aware knowledge distillation loss that encourages the network to preserve the high-level place recognition knowledge. We also introduce a knowledge fusion module to integrate the knowledge of old and new models for LiDAR place recognition. Our extensive experiments demonstrate that KDF can be applied to different networks to overcome catastrophic forgetting, surpassing the state-of-the-art methods in terms of mean Recall@1 and forgetting score.
title Ranking-aware Continual Learning for LiDAR Place Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.07198