S$^3$Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-Localization
Read the original on arXiv Computer Vision →S$^3$Geo introduces a structure‑semantic synergistic learning framework for cross‑view geo‑localization, combining a Decoupled Query Pooling module to capture local structural patterns, an optimal‑transport based contrastive learning scheme for soft cross‑view correspondences, and a Semantic Knowledge Distillation strategy from a frozen CLIP teacher to embed semantic priors. The method jointly models fine‑grained structural and semantic information, enabling robust matching between images from vastly different viewpoints such as drone and satellite views. Experiments on University‑1652 and SUES‑200 datasets show that S$^3$Geo outperforms state‑of‑the‑art approaches without increasing inference complexity.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.