Multisource Joint Representation Learning Fusion Classification for Remote Sensing Images

Multisource remote sensing images provide complementary multidimensional information for reliable and accurate classification. However, gaps in imaging mechanisms result in heterogeneity between multiple source images. During fusion, this heterogeneity causes the generated multisource representations to be redundant and ignore discriminative unisource information, which significantly hampers the fusion classification performance. To address this challenge, we introduce a novel multisource joint representation learning method for remote sensing image fusion classification, termed multisource information bottleneck fusion network (MIBF-Net). Based on the information bottleneck principle, MIBF-Net uses mutual information constraints to effectively integrate multisource information, generating a comprehensive and nonredundant multisource representation. Specifically, MIBF-Net first introduces an attribution-driven noise adaptation layer to dynamically balance the speed of feature learning across sources for extracting discriminative unisource intrinsic information. Furthermore, a cross-source relationship encoding (CRE) module is designed to fully explore cross-source complex dependencies for enhancing the richness of fused representations. Finally, we design an information bottleneck fusion (IB-Fusion) module to fuse unisource semantic information and cross-source information while reducing redundancy. In particular, we use variational inference techniques to effectively address the mutual information optimization problem and provide theoretical derivations. Extensive experimental results on three heterogeneous multisource remote sensing data benchmarks show that the model significantly outperforms the state-of-the-art methods.