Open access
2026
Domain-Adaptive Vision–Language Learning for Semantic Remote Sensing Image–Text Retrieval
Results show that label-only remote sensing supervision can strengthen scene-level semantic retrieval, but can also introduce directional negative transfer when the auxiliary labels lack caption-level spatial and compositional detail.
A. Zaheer, Awais Ahmad, Sohail Jabbar et al.
· IEEE Journal of Selected Top... · 0 citations