Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
This addresses the problem of incorrect matching in remote sensing retrieval for domain-specific applications, representing an incremental improvement with novel method components.
The paper tackles the challenge of visual-semantic imbalance in remote sensing image-text retrieval by proposing the Direction-Oriented Visual-semantic Embedding Model (DOVE), which uses modules like ROAM and DTGA to align visual and textual representations, achieving verified effectiveness on benchmark datasets RSICD and RSITMD.
Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this problem, we propose a novel Direction-Oriented Visual-semantic Embedding Model (DOVE) to mine the relationship between vision and language. Our highlight is to conduct visual and textual representations in latent space, directing them as close as possible to a redundancy-free regional visual representation. Concretely, a Regional-Oriented Attention Module (ROAM) adaptively adjusts the distance between the final visual and textual embeddings in the latent semantic space, oriented by regional visual features. Meanwhile, a lightweight Digging Text Genome Assistant (DTGA) is designed to expand the range of tractable textual representation and enhance global word-level semantic connections using less attention operations. Ultimately, we exploit a global visual-semantic constraint to reduce single visual dependency and serve as an external constraint for the final visual and textual representations. The effectiveness and superiority of our method are verified by extensive experiments including parameter evaluation, quantitative comparison, ablation studies and visual analysis, on two benchmark datasets, RSICD and RSITMD.