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
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.
Forward citations
Cited by 8 Pith papers
-
From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection
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.
-
LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment
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.
-
EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition
EmbodiedPlace improves VPR re-ranking by learning how to mix features of candidate images selected through embodied constraints, with negligible added compute.
-
ImLPR: Image-based LiDAR Place Recognition using Vision Foundation Models
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.
-
Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensing
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.
-
SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models
SuperPlace demonstrates that improved classical aggregators (G2M and NVL-FT2) match or beat 2024-era VPR methods at much lower feature dimensions.
-
Feature Complementation Architecture for Visual Place Recognition
A CNN-ViT hybrid with frequency-spatial adapters and dynamic fusion is reported to reach new high Recall@1 scores on several VPR benchmarks.
-
Place Recognition Meet Multiple Modalitie: A Comprehensive Review, Current Challenges and Future Directions
A survey of visual, LiDAR, and cross-modal place recognition with a unified code library, but riddled with errors and disclaimer-ridden experimental comparisons.
Discussion (0). Sign in to comment.