4 papers
Learning the Target Priors Before Image Translation: A Decoupled Training Paradigm for Cross-Modal Image Translation in Remote Sensing
Keyan Hu, Mingtao Wang, Ziyu Zhou +4
Cross-modal image translation in remote sensing must preserve source-observed content while matching the target-domain distribution. Existing methods jointly learn the target prior…
LocationAgent: A Hierarchical Agent for Image Geolocation via Decoupling Strategy and Evidence from Parametric Knowledge
Qiujun Li, Zijin Xiao, Xulin Wang +3
Image geolocation aims to infer capture locations based on visual content. Fundamentally, this constitutes a reasoning process composed of \textit{hypothesis-verification cycles},…
SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters
Jiahao Cui, Jiale Duan, Binyan Luo +3
Deep neural network-based Synthetic Aperture Radar (SAR) target recognition models are susceptible to adversarial examples. Current adversarial example generation methods for SAR i…
Using Global Land Cover Product as Prompt for Cropland Mapping via Visual Foundation Model
Chao Tao, Aoran Hu, Rong Xiao +2
Data-driven deep learning methods have shown great potential in cropland mapping. However, due to multiple factors such as attributes of cropland (topography, climate, crop type) a…