Saved in:
Bibliographic Details
Main Authors: Xia, Yan, Li, Zhendong, Li, Yun-Jin, Shi, Letian, Cao, Hu, Henriques, João F., Cremers, Daniel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.12079
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910747812954112
author Xia, Yan
Li, Zhendong
Li, Yun-Jin
Shi, Letian
Cao, Hu
Henriques, João F.
Cremers, Daniel
author_facet Xia, Yan
Li, Zhendong
Li, Yun-Jin
Shi, Letian
Cao, Hu
Henriques, João F.
Cremers, Daniel
contents To date, most place recognition methods focus on single-modality retrieval. While they perform well in specific environments, cross-modal methods offer greater flexibility by allowing seamless switching between map and query sources. It also promises to reduce computation requirements by having a unified model, and achieving greater sample efficiency by sharing parameters. In this work, we develop a universal solution to place recognition, UniLoc, that works with any single query modality (natural language, image, or point cloud). UniLoc leverages recent advances in large-scale contrastive learning, and learns by matching hierarchically at two levels: instance-level matching and scene-level matching. Specifically, we propose a novel Self-Attention based Pooling (SAP) module to evaluate the importance of instance descriptors when aggregated into a place-level descriptor. Experiments on the KITTI-360 dataset demonstrate the benefits of cross-modality for place recognition, achieving superior performance in cross-modal settings and competitive results also for uni-modal scenarios. Our project page is publicly available at https://yan-xia.github.io/projects/UniLoc/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_12079
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UniLoc: Towards Universal Place Recognition Using Any Single Modality
Xia, Yan
Li, Zhendong
Li, Yun-Jin
Shi, Letian
Cao, Hu
Henriques, João F.
Cremers, Daniel
Computer Vision and Pattern Recognition
To date, most place recognition methods focus on single-modality retrieval. While they perform well in specific environments, cross-modal methods offer greater flexibility by allowing seamless switching between map and query sources. It also promises to reduce computation requirements by having a unified model, and achieving greater sample efficiency by sharing parameters. In this work, we develop a universal solution to place recognition, UniLoc, that works with any single query modality (natural language, image, or point cloud). UniLoc leverages recent advances in large-scale contrastive learning, and learns by matching hierarchically at two levels: instance-level matching and scene-level matching. Specifically, we propose a novel Self-Attention based Pooling (SAP) module to evaluate the importance of instance descriptors when aggregated into a place-level descriptor. Experiments on the KITTI-360 dataset demonstrate the benefits of cross-modality for place recognition, achieving superior performance in cross-modal settings and competitive results also for uni-modal scenarios. Our project page is publicly available at https://yan-xia.github.io/projects/UniLoc/.
title UniLoc: Towards Universal Place Recognition Using Any Single Modality
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12079