Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
ConvVitMamba, a hybrid CNN-Transformer-Mamba architecture, is introduced for hyperspectral image (HSI) classification to address the computational limitations of existing methods. It combines multiscale convolutional feature extraction, Vision Transformer-based tokenization, and a Mamba-inspired gated sequence mixing module. Experiments on four benchmark datasets show that ConvVitMamba outperforms CNN, Transformer, and Mamba baselines while maintaining a favorable balance between accuracy, model size, and inference efficiency.
ConvVitMamba proves that a carefully crafted hybrid architecture leveraging CNNs, Transformers, and Mamba can achieve state-of-the-art hyperspectral image classification with improved efficiency.
Hyperspectral image (HSI) classification remains challenging due to high spectral dimensionality, redundancy, and limited labeled data. Although convolutional neural networks (CNNs) and Vision Transformers (ViTs) achieve strong performance by exploiting spectral-spatial information and long-range dependencies, they often incur high computational cost and large model size, limiting practical use. To address these limitations, a unified hybrid framework, termed ConvVitMamba, is proposed for efficient HSI classification. The architecture integrates three components: a multiscale convolutional feature extractor to capture local spectral, spatial, and joint patterns; a Vision Transformer based tokenization and encoding stage to model global contextual relationships; and a lightweight Mamba inspired gated sequence mixing module for efficient content-aware refinement without quadratic self-attention. Principal Component Analysis (PCA) is used as preprocessing to reduce redundancy and improve efficiency. Experiments on four benchmark datasets, including Houston and three UAV borne QUH datasets (Pingan, Qingyun, and Tangdaowan), demonstrate that ConvVitMamba consistently outperforms CNN, Transformer, and Mamba based methods while maintaining a favorable balance between accuracy, model size, and inference efficiency. Ablation studies confirm the complementary contributions of all components. The results indicate that the proposed framework provides an effective and efficient solution for HSI classification in diverse scenarios. The source code is publicly available at https://github.com/mqalkhatib/ConvVitMamba