PMPGuard: Catching Pseudo-Matched Pairs in Remote Sensing Image-Text Retrieval
This addresses noisy data challenges in remote sensing retrieval, but it is incremental as it builds on existing methods for handling mismatches.
The paper tackles the problem of Pseudo-Matched Pairs (PMPs) in remote sensing image-text retrieval, which hinder cross-modal alignment, and proposes a framework using Cross-Modal Gated Attention and Positive-Negative Awareness Attention to mitigate these issues, achieving state-of-the-art performance on three benchmark datasets.
Remote sensing (RS) image-text retrieval faces significant challenges in real-world datasets due to the presence of Pseudo-Matched Pairs (PMPs), semantically mismatched or weakly aligned image-text pairs, which hinder the learning of reliable cross-modal alignments. To address this issue, we propose a novel retrieval framework that leverages Cross-Modal Gated Attention and a Positive-Negative Awareness Attention mechanism to mitigate the impact of such noisy associations. The gated module dynamically regulates cross-modal information flow, while the awareness mechanism explicitly distinguishes informative (positive) cues from misleading (negative) ones during alignment learning. Extensive experiments on three benchmark RS datasets, i.e., RSICD, RSITMD, and RS5M, demonstrate that our method consistently achieves state-of-the-art performance, highlighting its robustness and effectiveness in handling real-world mismatches and PMPs in RS image-text retrieval tasks.