Hyperspectral anomaly detection (HAD) is widely used in Earth observation and deep space exploration. A major challenge for HAD is the complex background of the input hyperspectral images (HSIs), resulting in anomalies confused in the background. On the other hand, the lack of labeled samples for HSIs leads to poor generalization of existing HAD methods. This paper starts the first attempt to study a new and generalizable background learning problem without labeled samples. We present a novel solution BSDM (background suppression diffusion model) for HAD, which can simultaneously learn latent background distributions and generalize to different datasets for suppressing complex background. It is featured in three aspects: (1) For the complex background of HSIs, we design pseudo background noise and learn the potential background distribution in it with a diffusion model (DM). (2) For the generalizability problem, we apply a statistical offset module so that the BSDM adapts to datasets of different domains without labeling samples. (3) For achieving background suppression, we innovatively improve the inference process of DM by feeding the original HSIs into the denoising network, which removes the background as noise. Our work paves a new background suppression way for HAD that can improve HAD performance without the prerequisite of manually labeled data. Assessments and generalization experiments of four HAD methods on several real HSI datasets demonstrate the above three unique properties of the proposed method. The code is available at https://github.com/majitao-xd/BSDM-HAD.

翻译：高光谱异常检测（HAD）广泛应用于地球观测和深空探测领域。输入高光谱图像（HSI）中复杂的背景是HAD面临的主要挑战，这导致异常信息与背景混淆。此外，高光谱图像缺乏标注样本导致现有HAD方法泛化能力较差。本文首次尝试研究一种无需标注样本的通用背景学习新问题。我们提出了一种创新的BSDM（背景抑制扩散模型）解决方案，该模型能够同时学习潜在背景分布并泛化至不同数据集以抑制复杂背景。其特色体现在三个方面：（1）针对HSI的复杂背景，我们设计伪背景噪声，并利用扩散模型（DM）学习其中的潜在背景分布；（2）为解决泛化问题，我们引入统计偏移模块，使BSDM无需标注样本即可适应不同域的数据集；（3）为实现背景抑制，我们创新性地改进DM推理过程，将原始HSI输入去噪网络，将背景作为噪声去除。本研究为HAD开辟了新的背景抑制途径，可在无需人工标注数据的条件下提升HAD性能。基于四种HAD方法在多个真实HSI数据集上的评估与泛化实验，验证了所提方法的上述三个独特特性。代码开源地址：https://github.com/majitao-xd/BSDM-HAD。