Papers › Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition

Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition

22 Feb 2024arXiv:2402.14505archive 2025-07-28

Feng Lu, Lijun Zhang, Xiangyuan Lan, Shuting Dong, YaoWei Wang, Chun Yuan

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 nearest neighbor local feature loss, which ensures proper dense local features are produced for local matching and avoids time-consuming spatial verification in re-ranking. Experimental results show that our method outperforms the state-of-the-art methods with less training data and training time, and uses about only 3% retrieval runtime of the two-stage VPR methods with RANSAC-based spatial verification. It ranks 1st on the MSLS challenge leaderboard (at the time of submission). The code is released at https://github.com/Lu-Feng/SelaVPR.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Lu-Feng/SelaVPR officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Re-RankingVisual Place Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Place Recognition Mapillary test SelaVPR Recall@1 73.5 #9 of 12 Archive leaderboard report
Visual Place Recognition Mapillary test SelaVPR Recall@10 90.6 #9 of 12 Archive leaderboard report
Visual Place Recognition Mapillary test SelaVPR Recall@5 87.5 #9 of 12 Archive leaderboard report
Visual Place Recognition Mapillary val SelaVPR Recall@1 90.8 #10 of 18 Archive leaderboard report
Visual Place Recognition Mapillary val SelaVPR Recall@10 97.2 #10 of 18 Archive leaderboard report
Visual Place Recognition Mapillary val SelaVPR Recall@5 96.4 #10 of 18 Archive leaderboard report
Visual Place Recognition Nordland SelaVPR Recall@1 86.6 #6 of 13 Archive leaderboard report
Visual Place Recognition Nordland SelaVPR Recall@5 94.0 #6 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-250k-test SelaVPR Recall@1 95.7 #5 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-250k-test SelaVPR Recall@10 98.8 #5 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-250k-test SelaVPR Recall@5 99.2 #5 of 13 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test SelaVPR Recall@1 92.8 #10 of 22 Archive leaderboard report
Visual Place Recognition Pittsburgh-30k-test SelaVPR Recall@5 97.7 #10 of 22 Archive leaderboard report
Visual Place Recognition St Lucia SelaVPR Recall@1 99.8 #5 of 14 Archive leaderboard report
Visual Place Recognition Tokyo247 SelaVPR Recall@1 94.0 #8 of 14 Archive leaderboard report
Visual Place Recognition Tokyo247 SelaVPR Recall@10 96.8 #8 of 14 Archive leaderboard report
Visual Place Recognition Tokyo247 SelaVPR Recall@5 97.5 #8 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections