SpectralMamba：面向高光谱图像分类的高效Mamba模型
SpectralMamba: Efficient Mamba for Hyperspectral Image Classification
AI总结：
针对现有高光谱图像分类序列模型效率低的问题，提出SpectralMamba框架，通过双层动态建模与分段扫描机制，在4个基准数据集上实现了性能与效率的双赢。
摘要：
循环神经网络与Transformer凭借捕获光谱序列长距离依赖关系的能力，近期在高光谱（HS）成像领域的多数应用中占据主导地位。然而，尽管这类序列架构取得了成功，并行化困难或注意力机制计算成本过高带来的不可忽视的低效问题，仍阻碍着其实用性，尤其在遥感场景的大规模观测任务中受限明显。\n为解决这一问题，本文提出SpectralMamba——一种融合新型状态空间模型的高效深度学习框架，用于高光谱图像分类。SpectralMamba的核心特点是在两个层级对高光谱数据的动态特性进行简化且充分的建模：其一，在空谱空间中，通过高效卷积学习动态掩码，同时编码空间规律性与光谱特异性，从而减轻判别性表征学习中的光谱变异性与混淆问题；其二，融合后的光谱可在隐状态空间中高效运算，所有参数的学习均依赖输入，无需冗余注意力机制或无法并行的循环结构，即可生成选择性聚焦的响应。\n为进一步探索压缩计算量的空间，模型中间采用分段扫描机制，将近似连续的光谱转换为长度压缩的序列，同时保留数百个波段间的短期与长期上下文特征。通过在卫星、飞机及无人机载成像仪获取的4个基准高光谱数据集上开展的大量实验，SpectralMamba出人意料地在性能与效率两方面均实现了极具前景的双赢效果。
英文摘要：
Recurrent neural networks and Transformers have recently dominated most applications in hyperspectral (HS) imaging, owing to their capability to capture long-range dependencies from spectrum sequences. However, despite the success of these sequential architectures, the non-ignorable inefficiency caused by either difficulty in parallelization or computationally prohibitive attention still hinders their practicality, especially for large-scale observation in remote sensing scenarios. To address this issue, we herein propose SpectralMamba -- a novel state space model incorporated efficient deep learning framework for HS image classification. SpectralMamba features the simplified but adequate modeling of HS data dynamics at two levels. First, in spatial-spectral space, a dynamical mask is learned by efficient convolutions to simultaneously encode spatial regularity and spectral peculiarity, thus attenuating the spectral variability and confusion in discriminative representation learning. Second, the merged spectrum can then be efficiently operated in the hidden state space with all parameters learned input-dependent, yielding selectively focused responses without reliance on redundant attention or imparallelizable recurrence. To explore the room for further computational downsizing, a piece-wise scanning mechanism is employed in-between, transferring approximately continuous spectrum into sequences with squeezed length while maintaining short- and long-term contextual profiles among hundreds of bands. Through extensive experiments on four benchmark HS datasets acquired by satellite-, aircraft-, and UAV-borne imagers, SpectralMamba surprisingly creates promising win-wins from both performance and efficiency perspectives.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
