HC-Mamba: Remote Sensing Image Classification via Hybrid Cross-Activation State–Space Model

Remote sensing image classification plays a crucial role in scene understanding task interpretation. Currently, remote sensing image classification is constrained by the complexity, diversity, and time-varying nature of the scene as well as the variability of spatiotemporal resolution while the classification detection accuracy is difficult to be further improved. In this article, a new hybrid cross-activation network (HC-Mamba) is proposed based on the visual state–space model represented by Mamba to further improve the understanding of image collation and provide more quasiclustered semantic cues for scene recognition. First, we further improve the classification performance by combining the features of hardware-aware design, global receptive domain, and linear modeling complexity. Second, we propose a local content enrichment module to learn to distinguish local features to maintain the essential characteristics of image sequences. Finally, we propose a dynamic hybrid cross-activation mechanism to counteract the limitations of causal sequence modeling that makes it difficult to adapt to 2-D image data, and further improve the model's ability to model noncausal data. In addition, HC-Mamba maintains the inherent modeling mechanism of the original model, and demonstrates better performance on three benchmark remote sensing image classification data through a large number of experiments, which indicates that our proposed model has a great potential for the backbone network in future visualization-based modeling work.