arXiv 2407.068412024-07-17cs.CV

HTD-Mamba：基于金字塔状态空间模型的高效高光谱目标检测

HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space Model

DUT Artificial Intelligence Institute（大连理工大学人工智能学院）；Dalian Key Laboratory of Artificial Intelligence（大连市人工智能重点实验室）；Jiangnan University（江南大学）；Jiangsu Provincial Engineering Laboratory for Pattern Recognition and Computational Intelligence（江苏省模式识别与计算智能工程实验室）

Dunbin Shen, Xuanbing Zhu, Jiacheng Tian, Jianjun Liu, Zhenrong Du, Hongyu Wang, Xiaorui Ma

备注：: 13 pages,6 figures, 5 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对高光谱目标检测中先验不足和光谱变异导致的性能问题，提出HTD-Mamba，采用光谱对比学习和金字塔状态空间模型，首次将Mamba用于高光谱目标检测，在四个公开数据集上优于现有方法。

摘要：

高光谱目标检测（HTD）在像素级别上从复杂背景中识别感兴趣的目标，在地球观测中发挥着至关重要的作用。然而，由于先验知识有限和光谱变异，HTD面临挑战，导致模型欠拟合和性能不可靠。为了解决这些问题，本文提出了一种高效的自监督HTD方法，采用金字塔状态空间模型（SSM），命名为HTD-Mamba，该方法利用光谱对比学习，基于内在特征的相似性度量来区分目标和背景。具体而言，为了获得足够的训练样本并利用空间上下文信息，我们提出了一种空间编码光谱增强技术，将补丁内所有周围像素编码为中心像素的变换视图。此外，为了探索全局波段相关性，我们将像素划分为连续的组间光谱嵌入，并首次将Mamba引入HTD，以线性复杂度建模光谱序列的长程依赖关系。进一步地，为了减轻光谱变异并增强鲁棒表示，我们提出了一种金字塔SSM作为骨干网络，以捕获并融合多分辨率的光谱内在特征。在四个公开数据集上进行的大量实验表明，所提出的方法在定量和定性评估中均优于最先进的方法。代码可在https://github.com/shendb2022/HTD-Mamba获取。

英文摘要：

Hyperspectral target detection (HTD) identifies objects of interest from complex backgrounds at the pixel level, playing a vital role in Earth observation. However, HTD faces challenges due to limited prior knowledge and spectral variation, leading to underfitting models and unreliable performance. To address these challenges, this paper proposes an efficient self-supervised HTD method with a pyramid state space model (SSM), named HTD-Mamba, which employs spectrally contrastive learning to distinguish between target and background based on the similarity measurement of intrinsic features. Specifically, to obtain sufficient training samples and leverage spatial contextual information, we propose a spatial-encoded spectral augmentation technique that encodes all surrounding pixels within a patch into a transformed view of the center pixel. Additionally, to explore global band correlations, we divide pixels into continuous group-wise spectral embeddings and introduce Mamba to HTD for the first time to model long-range dependencies of the spectral sequence with linear complexity. Furthermore, to alleviate spectral variation and enhance robust representation, we propose a pyramid SSM as a backbone to capture and fuse multiresolution spectral-wise intrinsic features. Extensive experiments conducted on four public datasets demonstrate that the proposed method outperforms state-of-the-art methods in both quantitative and qualitative evaluations. Code is available at \url{https://github.com/shendb2022/HTD-Mamba}.

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。