Positive Matching Benefits Fusion: A Novel Contrastive Learning Framework for Hyperspectral and LiDAR Data Classification

Recent advancements in contrastive learning have led to significant progress in multi-modal remote sensing data classification, such as hyperspectral and LiDAR data, particularly in scenarios with limited labeled samples. However, these methods primarily rely on the contrast between positive and negative pairs, which makes them susceptible to interference from negative sample selection, thereby impairing effective multi-modal fusion and ultimately affecting classification accuracy. To address this issue, this paper introduces a novel framework for the joint classification of hyperspectral image (HSI) and LiDAR, termed the multi-Positive Matching-enhanced Contrastive Learning (mPMCL). The proposed framework facilitates contrastive training by matching multiple positive pairs across different modalities and hierarchical features of the same object, hence effectively enhancing multi-modal fusion and improving classification performance. Specifically, the HCIF module performs hierarchical and consistency-aware fusion by using a bidirectional cross-attention mechanism to integrate low-level, cross-modal interaction, and high-level semantic features from HSI and LiDAR data. This process gradually aligns heterogeneous representations across stages and captures complementary spectral–elevation cues, leading to more stable and discriminative multimodal features. Additionally, a multi-Positive Matching Strategy (mPMS) is develpoed to construct multiple positive pairs by matching high-level semantic features of the same object with low-level- and cross-modal fusion features from different modalities. By performing contrastive training on these positive pairs, the proposed method avoids the sensitivity of traditional approaches to negative sample selection, while further enhancing the effectiveness of multi-modal information fusion. The pivotal contribution of the proposed framework lies in demonstrating the importance of positive matching enhanced contrastive learning strategies for effective multi-modal information fusion. Experimental results on several publicly available datasets show that the proposed framework outperforms existing state-of-the-art methods. Our code is publicly available at https://github.com/HoppouCJ/mPMCL.