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.
@article{arxiv.2401.16304,
title = {Regressing Transformers for Data-efficient Visual Place Recognition},
author = {María Leyva-Vallina and Nicola Strisciuglio and Nicolai Petkov},
journal= {arXiv preprint arXiv:2401.16304},
year = {2024}
}