EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918329047842816 |
|---|---|
| author | Tzachor, Issar Lerner, Boaz Levy, Matan Green, Michael Shalev, Tal Berkovitz Habib, Gavriel Samuel, Dvir Zailer, Noam Korngut Shimshi, Or Darshan, Nir Ben-Ari, Rami |
| author_facet | Tzachor, Issar Lerner, Boaz Levy, Matan Green, Michael Shalev, Tal Berkovitz Habib, Gavriel Samuel, Dvir Zailer, Noam Korngut Shimshi, Or Darshan, Nir Ben-Ari, Rami |
| contents | The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like DINOv2 for the VPR task. However, these models are often deemed inadequate for VPR without further fine-tuning on VPR-specific data. In this paper, we present an effective approach to harness the potential of a foundation model for VPR. We show that features extracted from self-attention layers can act as a powerful re-ranker for VPR, even in a zero-shot setting. Our method not only outperforms previous zero-shot approaches but also introduces results competitive with several supervised methods. We then show that a single-stage approach utilizing internal ViT layers for pooling can produce global features that achieve state-of-the-art performance, with impressive feature compactness down to 128D. Moreover, integrating our local foundation features for re-ranking further widens this performance gap. Our method also demonstrates exceptional robustness and generalization, setting new state-of-the-art performance, while handling challenging conditions such as occlusion, day-night transitions, and seasonal variations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18065 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition Tzachor, Issar Lerner, Boaz Levy, Matan Green, Michael Shalev, Tal Berkovitz Habib, Gavriel Samuel, Dvir Zailer, Noam Korngut Shimshi, Or Darshan, Nir Ben-Ari, Rami Computer Vision and Pattern Recognition Artificial Intelligence The task of Visual Place Recognition (VPR) is to predict the location of a query image from a database of geo-tagged images. Recent studies in VPR have highlighted the significant advantage of employing pre-trained foundation models like DINOv2 for the VPR task. However, these models are often deemed inadequate for VPR without further fine-tuning on VPR-specific data. In this paper, we present an effective approach to harness the potential of a foundation model for VPR. We show that features extracted from self-attention layers can act as a powerful re-ranker for VPR, even in a zero-shot setting. Our method not only outperforms previous zero-shot approaches but also introduces results competitive with several supervised methods. We then show that a single-stage approach utilizing internal ViT layers for pooling can produce global features that achieve state-of-the-art performance, with impressive feature compactness down to 128D. Moreover, integrating our local foundation features for re-ranking further widens this performance gap. Our method also demonstrates exceptional robustness and generalization, setting new state-of-the-art performance, while handling challenging conditions such as occlusion, day-night transitions, and seasonal variations. |
| title | EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2405.18065 |