Pith. sign in

REVIEW 8 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.14505 v3 pith:4N7LQ5UO submitted 2024-02-22 cs.CV cs.AI

classification cs.CVcs.AI
keywords pre-trainedadaptationlocalmodelsvisualdatamethodtraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    ProteusVPR is a retrieval-plus-geometric-refinement framework that cuts mean localization error by over 60% on average for cross-scene maritime VPR and is evaluated on the new XHZ ship-borne panoramic dataset.

  2. LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment

    cs.CV 2025-07 conditional novelty 6.0 of 10

    LoD-Loc v2 localizes aerial cameras by aligning predicted building silhouettes with rendered low-detail city-model silhouettes, achieving accurate 4-DoF pose without textured maps.

  3. EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition

    cs.CV 2025-06 reject novelty 6.0 of 10

    EmbodiedPlace improves VPR re-ranking by learning how to mix features of candidate images selected through embodied constraints, with negligible added compute.

  4. ImLPR: Image-based LiDAR Place Recognition using Vision Foundation Models

    cs.RO 2025-05 conditional novelty 6.0 of 10

    A frozen DINOv2 vision foundation model, adapted with lightweight MultiConv adapters on a three-channel range image view of LiDAR scans, achieves state-of-the-art LiDAR place recognition and generalizes across sensors.

  5. Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensing

    cs.CV 2025-07 reject novelty 5.0 of 10

    A 3DGS-based aerial visual relocalization pipeline reports strong accuracy, but its 100 percent recall after filtering is achieved by excluding hard queries from the evaluation.

  6. SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models

    cs.CV 2025-06 conditional novelty 5.0 of 10

    SuperPlace demonstrates that improved classical aggregators (G2M and NVL-FT2) match or beat 2024-era VPR methods at much lower feature dimensions.

  7. Feature Complementation Architecture for Visual Place Recognition

    cs.CV 2025-06 reject novelty 5.0 of 10

    A CNN-ViT hybrid with frequency-spatial adapters and dynamic fusion is reported to reach new high Recall@1 scores on several VPR benchmarks.

  8. Place Recognition Meet Multiple Modalitie: A Comprehensive Review, Current Challenges and Future Directions

    cs.CV 2025-05 reject novelty 4.0 of 10

    A survey of visual, LiDAR, and cross-modal place recognition with a unified code library, but riddled with errors and disclaimer-ridden experimental comparisons.

Pith tools