P${}^2$Cal: A Prior-Posterior Collaborative Calibration Framework for Robust Remote Sensing Image-Text Retrieval

Remote sensing image-text retrieval (RSITR) aims to match remote sensing images with their corresponding natural language descriptions. Existing methods primarily focus on learning a discriminative cross-modal space, while paying insufficient attention to the collaborative calibration of image-text correspondences at the levels of prior supervision and posterior scores. Such calibration can facilitate both the learning of this space and the subsequent refinement of retrieval scores. To address this limitation, we propose P${}^2$Cal, a prior-posterior collaborative calibration framework for robust RSITR. Specifically, we first propose a Prior Semantic Calibration Module (PSCM), which purifies supervision through prior semantic calibration to obtain highly reliable supervisory signals. These signals are then used to train our proposed Manifold Residual Adapter (MRA) and Posterior Score Calibration Flow (PSCF). MRA incorporates lightweight manifold residual adapters into the representation pathways to construct a stable discriminative score space. PSCF takes the resulting matching scores as its initial state and learns a continuous residual velocity field to progressively optimize retrieval scores. Extensive experiments on multiple RSITR datasets demonstrate that P${}^2$Cal consistently outperforms existing state-of-the-art methods.