4 papers
FAST: Flow Any Scene Transformer
Yongjian Zhang, Longguang Wang, Zhuo Song +3
Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains underexplored. In this work, we pr…
Warp-free Cross-view Geo-localization via Feature-space Consensus Mining
Zhuo Song, Lian Xu, Runqing Jiang +4
Cross-view geo-localization is challenging due to drastic viewpoint changes and large appearance discrepancies between street-level and satellite imagery. Although existing methods…
A Unified Hierarchical Framework for Fine-grained Cross-view Geo-localization over Large-scale Scenarios
Zhuo Song, Ye Zhang, Kunhong Li +2
Cross-view geo-localization is a promising solution for large-scale localization problems, requiring the sequential execution of retrieval and metric localization tasks to achieve…
Pack-PTQ: Advancing Post-training Quantization of Neural Networks by Pack-wise Reconstruction
Changjun Li, Runqing Jiang, Zhuo Song +3
Post-training quantization (PTQ) has evolved as a prominent solution for compressing complex models, which advocates a small calibration dataset and avoids end-to-end retraining. H…