Abstract
Hyperspectral anomaly detection (HAD) remains a critical challenge in remote sensing, aiming to precisely separate sparse, unknown anomalies from complex, high-proportion backgrounds. Although deep learning architectures, particularly the Transformer, dominate HAD, their effectiveness is constrained by two fundamental deficiencies: the architectural flaw of “uniform processing” across feature tokens and the microscopic reliance on fixed non-linear activation functions, which are mathematically insufficient for modeling the complex HSI spectral features. To address this dual challenge, this paper introduces the Synergistic Kolmogorov–Arnold Network and Fidelity-Gated Transformer (KANGT) framework. This novel framework integrates two synergistic innovations: the Fidelity-Gated Context-Aware Transformer (GCAT), which employs a reconstruction fidelity-based gating module named the Contextual Feature Matching Module (CFMM) to explicitly and dynamically separate background and anomaly processing streams, and the KAN-MLP module, which replaces traditional Feed-Forward Networks (FFNs) with learnable, spline-based functions, enabling superior adaptive non-linear feature approximation. Extensive experiments on challenging real-world HSI datasets consistently demonstrate KANGT’s superior performance compared to existing methods, and the average AUC reached 0.9921 on eight datasets. This work establishes a robust new paradigm for HAD, with future efforts aimed at optimizing the computational efficiency of KANs to meet real-time application demands.