arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.19787cs.CV
收藏

JIST:面向序列视觉地点识别的图像与序列联合训练

JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition

Politecnico di Torino(都灵理工大学)

Gabriele Berton, Gabriele Trivigno, Barbara Caputo, Carlo Masone

AI总结:

本文提出JIST协议,通过多任务学习利用大规模无标注图像训练序列视觉地点识别,并引入SeqGeM聚合层生成紧凑嵌入,在速度、描述符大小和架构轻量性上均优于现有方法。

摘要:

视觉地点识别旨在依靠视觉线索识别先前访问过的地点,并在机器人应用中用于SLAM和定位。由于移动机器人通常可以获取连续的帧流,该任务自然被表述为序列到序列的定位问题。然而,获取带标签的序列数据比收集孤立图像昂贵得多,而孤立图像可以在很少监督的情况下自动完成。为了缓解这一问题,我们提出了一种新颖的联合图像与序列训练协议(JIST),该协议通过多任务学习框架利用大规模未经整理的图像集。借助JIST,我们还引入了SeqGeM,这是一种聚合层,重新审视了流行的GeM池化方法,以从单帧嵌入序列中生成一个鲁棒且紧凑的嵌入。我们表明,我们的模型能够超越以往的最先进方法,同时速度更快,使用的描述符小8倍,架构更轻量,并且能够处理不同长度的序列。代码可在https://github.com/ga1i13o/JIST获取。

英文摘要:

Visual Place Recognition aims at recognizing previously visited places by relying on visual clues, and it is used in robotics applications for SLAM and localization. Since typically a mobile robot has access to a continuous stream of frames, this task is naturally cast as a sequence-to-sequence localization problem. Nevertheless, obtaining sequences of labelled data is much more expensive than collecting isolated images, which can be done in an automated way with little supervision. As a mitigation to this problem, we propose a novel Joint Image and Sequence Training protocol (JIST) that leverages large uncurated sets of images through a multi-task learning framework. With JIST we also introduce SeqGeM, an aggregation layer that revisits the popular GeM pooling to produce a single robust and compact embedding from a sequence of single-frame embeddings. We show that our model is able to outperform previous state of the art while being faster, using 8 times smaller descriptors, having a lighter architecture and allowing to process sequences of various lengths. Code is available at https://github.com/ga1i13o/JIST

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑