Cross-Attention-Driven Adaptive Graph Relational Network for Multilabel Remote Sensing Scene Classification

Multilabel remote sensing scene classification (MLRSSC) has garnered growing attention in recent years, owing to its more comprehensive description of land covers compared to its single-label counterpart. However, challenges arise inevitably. First, the relations among multiple scene labels are sophisticated. How to excavate the interclass dependencies is, therefore, a key challenge for the MLRSSC task. Second, extracting discriminative semantic features is essential, yet challenging for scene prediction of remote sensing images. Another issue is that the multilabel dataset usually shows twofold sample imbalances, that is, class imbalance and positive-negative imbalance, which have not been explored in MLRSSC tasks so far. To overcome the above hurdles, we put forward a cross-attention-driven adaptive graph relational network for the MLRSSC task. Different from the chain-like long short-term memory (LSTM) or static label co-occurrence matrices, we propose to use image-specific relational graphs to dynamically model the interclass dependencies. We innovatively devise a cross-attention-driven representation learning approach, which uses learnable label embeddings to query the class-wise semantic features, explicitly establishing the feature-label connections. Moreover, we design a balanced focal loss (BFL) function, where the loss contributions of positive and negative samples are rebalanced based on the respective imbalance degrees of diverse classes. Extensive experiments were performed on UCM, AID, and DFC15 multilabel datasets. Experimental results demonstrated that our proposed method achieves state-of-the-art performance in the studied task.