Abstract
Visual place recognition (VPR) aiming at predicting the location of an image based solely on its visual features is a fundamental task in robotics and autonomous systems. Domain variation remains one of the main challenges in VPR and is relatively unexplored. Existing VPR models attempt to achieve domain agnosticism either by training on large-scale datasets that inherently contain some domain variations, or by being specifically adapted to particular target domains. In practice, the former lacks explicit domain supervision, while the latter generalizes poorly to unseen domain shifts. This paper proposes a novel query-based domain-agnostic VPR model called QdaVPR. First, a dual-level adversarial learning framework is designed to encourage domain invariance for both the query features forming the global descriptor and the image features from which these query features are derived. Then, a triplet supervision based on query combinations is designed to enhance the discriminative power of the global descriptors. To support the learning process, we augment a large-scale VPR dataset using style transfer methods, generating various synthetic domains with corresponding domain labels as auxiliary supervision. Extensive experiments show that QdaVPR achieves state-of-the-art performance on multiple VPR benchmarks with significant domain variations. Specifically, it attains the best Recall@1 and Recall@10 on nearly all test scenarios: 93.5%/98.6% on Nordland (seasonal changes), 97.5%/99.0% on Tokyo24/7 (day-night transitions), and the highest Recall@1 across almost all weather conditions on the SVOX dataset. Our code will be released at this https URL.
Abstract (translated)
视觉位置识别（VPR）旨在仅基于图像的视觉特征预测其位置，这是机器人技术和自主系统中的一个基本任务。领域变化仍然是VPR的主要挑战之一，并且研究相对较少。现有的VPR模型试图通过在大规模数据集上进行训练来实现对领域的无感知性，这些数据集中固有地包含了一些领域变化，或者通过专门适应特定的目标域来进行这种尝试。实践中，前者缺乏明确的领域监督，而后者则难以泛化到未见的领域偏移中。 本文提出了一种新颖的查询基、领域无关型VPR模型——QdaVPR。首先设计了一个双层对抗性学习框架，该框架鼓励全局描述符中的查询特征以及这些查询特征所衍生出的图像特征达到领域不变性。其次，基于查询组合设计了三元监督机制，以增强全局描述符的区分能力。为了支持学习过程，我们通过使用风格迁移方法扩展了一大规模VPR数据集，生成多种合成域，并提供相应的领域标签作为辅助监督。 广泛的实验表明，QdaVPR在多个具有显著领域变化的VPR基准测试上实现了最佳性能。具体而言，在几乎所有的测试场景中，它达到了最好的Recall@1和Recall@10：Nordland（季节变化）为93.5%/98.6%，Tokyo24/7（昼夜转换）为97.5%/99.0%；在SVOX数据集的几乎所有天气条件下，它也取得了最高的Recall@1。我们的代码将在[此处发布](此链接应替换为实际提供的URL)。
URL
https://arxiv.org/abs/2603.07414
