Saved in:
Bibliographic Details
Main Authors: Izquierdo, Sergio, Civera, Javier
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.15937
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914849575927808
author Izquierdo, Sergio
Civera, Javier
author_facet Izquierdo, Sergio
Civera, Javier
contents The task of Visual Place Recognition (VPR) aims to match a query image against references from an extensive database of images from different places, relying solely on visual cues. State-of-the-art pipelines focus on the aggregation of features extracted from a deep backbone, in order to form a global descriptor for each image. In this context, we introduce SALAD (Sinkhorn Algorithm for Locally Aggregated Descriptors), which reformulates NetVLAD's soft-assignment of local features to clusters as an optimal transport problem. In SALAD, we consider both feature-to-cluster and cluster-to-feature relations and we also introduce a 'dustbin' cluster, designed to selectively discard features deemed non-informative, enhancing the overall descriptor quality. Additionally, we leverage and fine-tune DINOv2 as a backbone, which provides enhanced description power for the local features, and dramatically reduces the required training time. As a result, our single-stage method not only surpasses single-stage baselines in public VPR datasets, but also surpasses two-stage methods that add a re-ranking with significantly higher cost. Code and models are available at https://github.com/serizba/salad.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15937
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Optimal Transport Aggregation for Visual Place Recognition
Izquierdo, Sergio
Civera, Javier
Computer Vision and Pattern Recognition
The task of Visual Place Recognition (VPR) aims to match a query image against references from an extensive database of images from different places, relying solely on visual cues. State-of-the-art pipelines focus on the aggregation of features extracted from a deep backbone, in order to form a global descriptor for each image. In this context, we introduce SALAD (Sinkhorn Algorithm for Locally Aggregated Descriptors), which reformulates NetVLAD's soft-assignment of local features to clusters as an optimal transport problem. In SALAD, we consider both feature-to-cluster and cluster-to-feature relations and we also introduce a 'dustbin' cluster, designed to selectively discard features deemed non-informative, enhancing the overall descriptor quality. Additionally, we leverage and fine-tune DINOv2 as a backbone, which provides enhanced description power for the local features, and dramatically reduces the required training time. As a result, our single-stage method not only surpasses single-stage baselines in public VPR datasets, but also surpasses two-stage methods that add a re-ranking with significantly higher cost. Code and models are available at https://github.com/serizba/salad.
title Optimal Transport Aggregation for Visual Place Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.15937