Regressing Transformers for Data-efficient Visual Place Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911766845325312 |
|---|---|
| author | Leyva-Vallina, María Strisciuglio, Nicola Petkov, Nicolai |
| author_facet | Leyva-Vallina, María Strisciuglio, Nicola Petkov, Nicolai |
| contents | Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images and larger distance for dissimilar ones in a latent space. However, this approach struggles to ensure accurate distance-based image similarity representation, particularly when training with binary pairwise labels, and complex re-ranking strategies are required. This work introduces a fresh perspective by framing place recognition as a regression problem, using camera field-of-view overlap as similarity ground truth for learning. By optimizing image descriptors to align directly with graded similarity labels, this approach enhances ranking capabilities without expensive re-ranking, offering data-efficient training and strong generalization across several benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16304 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Regressing Transformers for Data-efficient Visual Place Recognition Leyva-Vallina, María Strisciuglio, Nicola Petkov, Nicolai Computer Vision and Pattern Recognition Machine Learning Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images and larger distance for dissimilar ones in a latent space. However, this approach struggles to ensure accurate distance-based image similarity representation, particularly when training with binary pairwise labels, and complex re-ranking strategies are required. This work introduces a fresh perspective by framing place recognition as a regression problem, using camera field-of-view overlap as similarity ground truth for learning. By optimizing image descriptors to align directly with graded similarity labels, this approach enhances ranking capabilities without expensive re-ranking, offering data-efficient training and strong generalization across several benchmark datasets. |
| title | Regressing Transformers for Data-efficient Visual Place Recognition |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.16304 |