تقرير
Regressing Transformers for Data-efficient Visual Place Recognition
| العنوان: | Regressing Transformers for Data-efficient Visual Place Recognition |
|---|---|
| المؤلفون: | Leyva-Vallina, María, Strisciuglio, Nicola, Petkov, Nicolai |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning |
| الوصف: | 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. Comment: Accepted for publication in ICRA 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2401.16304 |
| رقم الأكسشن: | edsarx.2401.16304 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |