GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priors
This addresses the costly need for ground truth data in adapting LiDAR place recognition models to new environments, offering a practical solution for robotics and autonomous systems in GPS-deprived areas.
The paper tackles the problem of performance degradation in LiDAR place recognition due to domain shift between training and test datasets, proposing GeoAdapt, a self-supervised test-time adaptation method that uses geometric priors to generate pseudo-labels, which significantly boosts performance across moderate to severe shifts and is competitive with fully supervised approaches.
LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak performance. However, obtaining accurate ground truth data for new training data can be prohibitively expensive, especially in complex or GPS-deprived environments. To address this issue we propose GeoAdapt, which introduces a novel auxiliary classification head to generate pseudo-labels for re-training on unseen environments in a self-supervised manner. GeoAdapt uses geometric consistency as a prior to improve the robustness of our generated pseudo-labels against domain shift, improving the performance and reliability of our Test-Time Adaptation approach. Comprehensive experiments show that GeoAdapt significantly boosts place recognition performance across moderate to severe domain shifts, and is competitive with fully supervised test-time adaptation approaches. Our code is available at https://github.com/csiro-robotics/GeoAdapt.