Deep learning has achieved remarkable success in hyperspectral image (HSI) classification, attributed to its powerful feature extraction capabilities. However, existing methods face several challenges: Convolutional Neural Networks (CNNs) are limited in modeling long-range spectral dependencies because of their limited receptive fields; Transformers are constrained by their quadratic computational complexity; and Mamba-based methods fail to fully exploit spatial–spectral interactions when handling high-dimensional HSI data. To address these limitations, we propose MRFP-Mamba, a novel Multi-Receptive-Field Parallel Mamba architecture that integrates hierarchical spatial feature extraction with efficient modeling of spatial–spectral dependencies. The proposed MRFP-Mamba introduces two key innovation modules: (1) A multi-receptive-field convolutional module employing parallel $1\times 1$, $3\times 3$, $5\times 5$, and $7\times 7$ kernels to capture fine-to-coarse spatial features, thereby improving discriminability for multi-scale objects; and (2) a parameter-optimized Vision Mamba branch that models global spatial–spectral relationships through structured state space mechanisms. Experimental results demonstrate that the proposed MRFP-Mamba consistently surpasses existing CNN-, Transformer-, and state space model (SSM)-based approaches across four widely used hyperspectral image (HSI) benchmark datasets: PaviaU, Indian Pines, Houston 2013, and WHU-Hi-LongKou. Compared with MambaHSI, our MRFP-Mamba achieves improvements in Overall Accuracy (OA) by 0.69%, 0.30%, 0.40%, and 0.97%, respectively, thereby validating its superior classification capability and robustness.

Deep learning methods have achieved remarkable success in remote sensing object detection. Existing object detection methods focus on integrating convolutional neural networks (CNNs) and Transformer networks to explore local and global representations to improve performance. However, existing methods relying on fixed convolutional kernels and dense global attention mechanisms suffer from computational redundancy and insufficient discriminative feature extraction, particularly for small and rotation-sensitive targets. To address these limitations, we propose a Dynamic Multi-Kernel Position-Aware Feature Pyramid Network (PAMFPN), which integrates adaptive sparse position modeling and multi-kernel dynamic fusion to achieve robust feature representation. Firstly, we design a position-interactive context module (PICM) that incorporates distance-aware sparse attention and dynamic positional encoding. It selectively focuses computation on sparse targets through a decay function that suppresses background noise while enhancing spatial correlations of critical regions. Secondly, we design a dual-kernel adaptive fusion (DKAF) architecture by combining region-sensitive attention (RSA) and reconfigurable context aggregation (RCA). RSA employs orthogonal large-kernel convolutions to capture anisotropic spatial features for arbitrarily oriented targets, while RCA dynamically adjusts the kernel scales based on content complexity, effectively addressing scale variations and intraclass diversity. Extensive experiments on three benchmark datasets (DOTA-v1.0, SSDD, HWPUVHR-10) demonstrate the effectiveness and versatility of the proposed PAMFPN. This work bridges the gap between efficient computation and robust feature fusion in remote sensing detection, offering a universal solution for real-world applications.

Deep learning has demonstrated significant success in hyperspectral image (HSI) classification by effectively leveraging spatial–spectral feature learning. However, current approaches encounter three challenges: (1) high spectral redundancy and the presence of noisy bands, which impair the extraction of discriminative features; (2) limited spatial receptive fields inherent in convolutional operations; and (3) unidirectional context modeling that inadequately captures bidirectional dependencies in non-causal HSI data. To address these challenges, this paper proposes HG-Mamba, a novel hybrid geometry-aware bidirectional Mamba network for HSI classification. The proposed HG-Mamba synergistically integrates convolutional operations, geometry-aware filtering, and bidirectional state-space models (SSMs) to achieve robust spectral–spatial representation learning. The proposed framework comprises two stages. The first stage, termed spectral compression and discrimination enhancement, employs multi-scale spectral convolutions alongside a spectral bidirectional Mamba (SeBM) module to suppress redundant bands while modeling long-range spectral dependencies. The second stage, designated spatial structure perception and context modeling, incorporates a Gaussian Distance Decay (GDD) mechanism to adaptively reweight spatial neighbors based on geometric distances, coupled with a spatial bidirectional Mamba (SaBM) module for comprehensive global context modeling. The GDD mechanism facilitates boundary-aware feature extraction by prioritizing spatially proximate pixels, while the bidirectional SSMs mitigate unidirectional bias through parallel forward–backward state transitions. Extensiveexperiments on the Indian Pines, Houston2013, and WHU-Hi-LongKou datasets demonstrate the superior performance of HG-Mamba, achieving overall accuracies of 94.91%, 98.41%, and 98.67%, respectively.

Recent advances in hyperspectral image (HSI) classification have demonstrated the effectiveness of hybrid architectures that integrate convolutional neural networks (CNNs) and Transformers, leveraging CNNs for local feature extraction and Transformers for global dependency modeling. However, existing fusion approaches face three critical challenges: (1) insufficient synergy between spectral and spatial feature learning due to rigid coupling mechanisms; (2) high computational complexity resulting from redundant attention calculations; and (3) limited adaptability to spectral redundancy and noise in small-sample scenarios. To address these limitations, we propose HyperTransXNet, a novel CNN-Transformer hybrid architecture that incorporates adaptive spectral-spatial fusion. Specifically, the proposed HyperTransXNet comprises three key modules: (1) a Hybrid Spatial-Spectral Module (HSSM) that captures the refined local spectral-spatial features and models global spectral correlations by combining depth-wise dynamic convolution with frequency-domain attention; (2) a Mixture-of-Experts Routing (MoE-R) module that adaptively fuses multi-scale features by dynamically selecting optimal experts via Top-K sparse weights; and (3) a Spatial-Spectral Tokens Enhancer (SSTE) module that ensures causality-preserving interactions between spectral bands and spatial contexts. Extensive experiments on the Indian Pines, Houston 2013, and WHU-Hi-LongKou datasets demonstrate the superiority of HyperTransXNet.