Towards Seamless Adaptation Of Pre-trained Models For Visual Place Recognition

Abstract

Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to exploit pre-trained foundation models in visual place recognition (VPR). Due to the inherent difference in training objectives and data between the tasks of model pre-training and VPR, how to bridge the gap and fully unleash the capability of pre-trained models for VPR is still a key issue to address. To this end, we propose a novel method to realize seamless adaptation of pre-trained models for VPR. Specifically, to obtain both global and local features that focus on salient landmarks for discriminating places, we design a hybrid adaptation method to achieve both global and local adaptation efficiently, in which only lightweight adapters are tuned without adjusting the pre-trained model. Besides, to guide effective adaptation, we propose a mutual neare

Stats

• citations0
• S2 citations—
• github stars263
• HF likes0
• heat score4.84
• arxiv keylu2024towards

Related papers

• Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• Structvpr++: Distill Structural And Semantic Knowledge With Weighting Samples For Visual Place Recognition (2025)3.58
• Structured Pruning For Efficient Visual Place Recognition (2024)2.26
• Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
• Attention-aware Age-agnostic Visual Place Recognition (2019)8.82
• Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70