解决激光雷达场景识别持续学习中的遗忘问题，提升长期记忆能力。
Ranking-aware Continual Learning for LiDAR Place Recognition
- 设计排名感知的蒸馏损失，保留关键场景识别知识
- 引入知识融合模块，有效整合新旧模型信息
- 在多个网络架构上验证，显著降低遗忘率
场景识别在SLAM、机器人导航和自动驾驶中具有重要意义。得益于深度学习，激光雷达场景识别（LPR）性能大幅提升。然而，现有基于学习的方法普遍存在灾难性遗忘问题，导致在新环境训练后，对先前场景的识别性能严重下降。本文提出一种基于知识蒸馏与融合（KDF）的持续学习框架，缓解遗忘问题。受场景检索中排名机制的启发，设计了排名感知的知识蒸馏损失，促使网络保持高层场景识别能力。同时引入知识融合模块，整合旧模型与新模型的知识。大量实验表明，KDF可应用于不同网络结构，在平均召回率@1和遗忘得分上均优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。