Learning from Mistakes: Loss-Aware Memory Enhanced Continual Learning for LiDAR Place Recognition

TL;DR

This paper introduces KDF+, a loss-aware, memory-augmented continual learning framework that improves LiDAR place recognition by effectively balancing new information learning and retention of previous knowledge.

Contribution

KDF+ extends existing continual learning methods with a loss-aware sampling and rehearsal enhancement, improving knowledge retention and adaptability in LiDAR place recognition.

Findings

KDF+ outperforms existing continual learning methods across multiple benchmarks.

The loss-aware sampling effectively selects informative samples for replay.

Rehearsal enhancement reinforces long-term knowledge retention.

Abstract

LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments without forgetting previously learned knowledge, a challenge widely known as catastrophic forgetting. To address this issue, we propose KDF+, a novel continual learning framework for LiDAR place recognition that extends the KDF paradigm with a loss-aware sampling strategy and a rehearsal enhancement mechanism. The proposed sampling strategy estimates the learning difficulty of each sample via its loss value and selects samples for replay according to their estimated difficulty. Harder samples, which tend to encode more discriminative information, are sampled with higher probability while maintaining distributional coverage across the dataset. In addition, the rehearsal enhancement mechanism encourages memory samples to be further refined during new-task training by slightly reducing their loss relative to previous tasks, thereby reinforcing long-term knowledge retention. Extensive experiments across multiple benchmarks demonstrate that KDF+ consistently outperforms existing continual learning methods and can be seamlessly integrated into state-of-the-art continual learning for LiDAR place recognition frameworks to yield significant and stable performance gains. The code will be available at https://github.com/repo/KDF-plus.