跳到正文
arXiv cs.AI· Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet, Nguyen Lam Phu Quy, Phu-Hoa Pham, Long Tran-Thanh·· 2 小时前AI 评分36

SKYPART:基于原型语义部件发现的天气鲁棒跨视角地理定位方法

Skypart : Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery

AI 导读

研究者提出 SKYPART,一种可即插即用的轻量级 ViT 头,通过可学习原型将图像块分组为语义部件,用于 GNSS 失效时的无人机跨视角地理定位。该方法仅 26.95M 参数、22.14 GFLOPs,是对比中体积最小的顶尖方法,在 SUES-200、University-1652 和 DenseUAV 上以单次检索(无重排序和 TTA)取得 SOTA。

正文 · 原文

View PDF HTML (experimental)

Abstract:The low-altitude economy is growing rapidly, increasing demand for reliable drone navigation. Common tasks such as delivery, inspection, and search-and-rescue rely on Global Navigation Satellite Systems (GNSS), which can be jammed, spoofed, or unavailable. Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, offers an alternative for autonomous localization when GNSS fails. However, current CVGL methods have three limitations: (1) global descriptors compress patch grids into a single vector, without separating cross-view-shared layout from view-specific texture; (2) altitude-related scale variation remains in the learned embedding instead of being marginalized as a nuisance; and (3) multi-objective training uses hand-tuned loss weights despite incompatible gradient scales. We propose SKYPART, a lightweight, swappable head for patch-based vision transformers (ViTs) that explicitly groups patches into parts. It combines (i) learnable prototypes that compete for patch tokens through single-pass cosine assignment; (ii) altitude-conditioned linear modulation used only during training, yielding altitude-free retrieval embeddings at inference; (iii) graph-attention readout over active prototypes; and (iv) Kendall uncertainty-weighted multi-objective learning that learns loss-group weights end-to-end. With 26.95M parameters and 22.14 GFLOPs, SKYPART is the smallest top-performing method in our comparison and achieves state-of-the-art results on SUES-200, University-1652, and DenseUAV using single-pass retrieval without reranking or test-time augmentation (TTA). Its accuracy advantage over the strongest baseline further increases under ten WeatherPrompt corruption conditions. Code: this https URL.
Comments: Accepted At Neurips 2026
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Robotics (cs.RO)
Cite as: arXiv:2605.11654 [cs.CV]
  (or arXiv:2605.11654v3 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2605.11654

arXiv-issued DOI via DataCite

Submission history

From: Duy Minh Dao Sy [view email]
[v1] Tue, 12 May 2026 07:15:52 UTC (29,980 KB)
[v2] Mon, 18 May 2026 13:48:57 UTC (29,972 KB)
[v3] Tue, 17 Nov 2026 17:23:25 UTC (31,227 KB)

来源:arXiv cs.AI · arxiv.org