Lightweight Cross-View Localization via Quantized Knowledge Distillation and Adaptive Local Feature Matching
IEEE Signal Processing Letters · 2026 · 33 · 1175-1179
DOI: 10.1109/lsp.2026.3670737 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Jialiang Shi und 6 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China.
Abstract (Originalsprache)
Despite notable progress in cross-view localization, extreme viewpoint differences between aerial and satellite imagery remain challenging. Existing methods often struggle to balance retrieval efficiency, matching accuracy, and model lightweightness. We propose a lightweight two-stage framework integrating efficient global retrieval with semantically-enhanced local matching. First, we adapt ternary quantized transformers to cross-view scenarios via progressive transfer learning, boosting retrieval without large-scale pretraining. Second, we introduce a dual-branch architecture that fuses texture and semantic features through cross-attention reasoning, employing semantic conditioning to filter mismatches from repetitive structures. Results on public datasets demonstrate improved localization accuracy and reduced computational cost, validating our framework’s suitability for resource-constrained UAVs.
Förderung
- National Natural Science Foundation of China
- National Key R&D Program of China
Zitieren
APA
Shi, J., Wang, Z., Zhang, C., Cheng, J., Lu, X., Li, L., & Li, Q. (2026). Lightweight Cross-View Localization via Quantized Knowledge Distillation and Adaptive Local Feature Matching. IEEE Signal Processing Letters, 33, 1175-1179. https://doi.org/10.1109/lsp.2026.3670737
Vancouver
Shi J, Wang Z, Zhang C, Cheng J, Lu X, Li L, et al. Lightweight Cross-View Localization via Quantized Knowledge Distillation and Adaptive Local Feature Matching. IEEE Signal Processing Letters. 2026;33:1175-1179. doi:10.1109/lsp.2026.3670737
BibTeX
@article{Shi2026,
author = {Shi, Jialiang and Wang, Zixu and Zhang, Chunxi and Cheng, Jingchun and Lu, Xin and Li, Lijing and Li, Qingzhe},
title = {Lightweight Cross-View Localization via Quantized Knowledge Distillation and Adaptive Local Feature Matching},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {1175--1179},
doi = {10.1109/lsp.2026.3670737}
}
EUVIMED