Towards classification-based representation learning for place recognition on LiDAR scans

TL;DR

This paper proposes a classification-based approach for place recognition using LiDAR scans, framing the task as a multi-class classification problem to improve training efficiency and stability, with competitive results on NuScenes.

Contribution

It introduces a novel classification-based method for LiDAR place recognition, contrasting with traditional contrastive learning approaches.

Findings

Achieves competitive accuracy on NuScenes dataset

Offers improved training efficiency and stability

Demonstrates the viability of classification for place recognition

Abstract

Place recognition is a crucial task in autonomous driving, allowing vehicles to determine their position using sensor data. While most existing methods rely on contrastive learning, we explore an alternative approach by framing place recognition as a multi-class classification problem. Our method assigns discrete location labels to LiDAR scans and trains an encoder-decoder model to classify each scan's position directly. We evaluate this approach on the NuScenes dataset and show that it achieves competitive performance compared to contrastive learning-based methods while offering advantages in training efficiency and stability.